© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14964
    Prev
    Next
    INDEX
    Explanations

    articles and pronouns

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act · gemini-2.0-flash

    the

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.05
     it
    -0.99
     an
    -0.88
     a
    -0.84
     the
    -0.79
     of
    -0.77
    ,
    -0.75
     that
    -0.69
     in
    -0.66
     he
    -0.66
    POSITIVE LOGITS
     Majefty
    1.23
     themſelves
    1.15
     Reſ
    1.12
     ſeveral
    1.11
     Diſ
    1.11
     ſhall
    1.08
     Efq
    1.08
     faſt
    1.06
     fhew
    1.05
     Monfieur
    1.05
    Activations Density 4.351%

    No Known Activations