© 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. 7229
    Prev
    Next
    INDEX
    Explanations

    sentences that refer to dates, publication and famous people

    oai_token-act-pair · gemini-2.0-flash

    terms related to publications or scientific works

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

    books and writings

    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
    TagMode
    -0.91
    ItemBackground
    -0.80
     ujednoznacz
    -0.73
    ыгана
    -0.71
     Houſe
    -0.70
     Majefty
    -0.69
    ValueStyle
    -0.69
    AnchorStyles
    -0.68
     Monfieur
    -0.66
     Jefus
    -0.66
    POSITIVE LOGITS
    +')
    0.47
     De
    0.44
     works
    0.43
    ))\
    0.41
    laceae
    0.41
     tratado
    0.41
    cope
    0.40
    Etimología
    0.40
    UIS
    0.39
    /'.$
    0.39
    Activations Density 1.204%

    No Known Activations