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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3365
    Prev
    Next
    INDEX
    Explanations

    legal or country names like, Congress, law, San or Russia

    oai_token-act-pair · gemini-2.0-flash

    San Francisco or sanctions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     San
    -2.67
    San
    -2.55
     san
    -2.42
     SAN
    -2.41
    san
    -2.34
    SAN
    -2.22
     Сан
    -1.77
    Сан
    -1.63
     sanction
    -1.55
     Sandi
    -1.38
    POSITIVE LOGITS
    ValueStyle
    0.66
     coreana
    0.59
    esModule
    0.59
    uxxxx
    0.54
     Arro
    0.54
     purpoſe
    0.53
     Ordovician
    0.52
    rrggbb
    0.52
    UserScript
    0.50
     Majefty
    0.50
    Activations Density 1.799%

    No Known Activations