© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11985
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and mentions of group membership

    oai_token-act-pair · gemini-2.0-flash

    here

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    rayage
    -0.65
    LookAnd
    -0.48
    èze
    -0.47
    참고
    -0.44
    hlungen
    -0.43
    ocarcinoma
    -0.42
     Quell
    -0.42
    nello
    -0.42
     sac
    -0.42
     VIDEOTAPE
    -0.41
    POSITIVE LOGITS
    principalColumn
    0.79
    Jeografia
    0.78
    Портал
    0.65
    kháu
    0.64
    Personendaten
    0.63
     useParams
    0.62
    //</
    0.60
    ⓘ
    0.59
     kaarangay
    0.58
    migrationBuilder
    0.56
    Activations Density 1.025%

    No Known Activations