© 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. 8547
    Prev
    Next
    INDEX
    Explanations

    proper nouns for organizations, particularly in the context of government or business

    oai_token-act-pair · gemini-2.0-flash

    programming terms or identifiers

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

    organizations

    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
    Geplaatst
    -0.64
    ,
    -0.51
    Brothers
    -0.38
     nación
    -0.38
    Handled
    -0.37
     while
    -0.37
     in
    -0.36
    .
    -0.36
     now
    -0.35
    ，
    -0.35
    POSITIVE LOGITS
     lenker
    0.92
    UnusedPrivate
    0.82
     Efq
    0.80
     myſelf
    0.77
    bardier
    0.77
    HomeAsUpEnabled
    0.75
     ujednoznacz
    0.75
    ChildScrollView
    0.74
    ſelf
    0.73
    NUMX
    0.72
    Activations Density 1.391%

    No Known Activations