© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9396
    Prev
    Next
    INDEX
    Explanations

    capitalized words in different contexts, including names, titles, and locations, especially when associated with historical or regal contexts

    oai_token-act-pair · gemini-2.0-flash

    technical terms or programming-related syntax

    np_token-act-pair-logits · gpt-4o-mini

    Historical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     correctes
    -0.58
     protoimpl
    -0.56
     مرئيه
    -0.55
     TextEditing
    -0.52
    dymyr
    -0.51
     Sonny
    -0.51
    thâu
    -0.50
    homonymie
    -0.50
     FetchType
    -0.48
     Aton
    -0.48
    POSITIVE LOGITS
    modelBuilder
    0.54
    umenta
    0.52
    ])),
    0.50
    varargin
    0.49
    mbggenerated
    0.49
    GEBURTSDATUM
    0.49
     guerres
    0.48
     Familienname
    0.48
     [*]
    0.47
    :"-
    0.47
    Activations Density 1.411%

    No Known Activations