© 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. 10608
    Prev
    Next
    INDEX
    Explanations

    mentions of living places and ethnic groups.

    oai_token-act-pair · gemini-2.0-flash

    ethnicities and living spaces

    np_max-act · gemini-2.0-flash

    French words

    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
     Anſ
    -0.80
    й
    -0.80
     Conſ
    -0.79
     Tutu
    -0.75
     Reſ
    -0.75
     Perſ
    -0.75
     rasc
    -0.75
     Pute
    -0.74
     Inſ
    -0.74
     itſelf
    -0.74
    POSITIVE LOGITS
    <bos>
    1.02
     dentaire
    0.90
    ungkinan
    0.88
     âgées
    0.83
    endsection
    0.82
     scolaire
    0.82
     dévelo
    0.81
     littéraire
    0.80
     touristique
    0.79
     spéciaux
    0.77
    Activations Density 2.613%

    No Known Activations