© 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. 12004
    Prev
    Next
    INDEX
    Explanations

    language expressing blame or responsibility

    oai_token-act-pair · gemini-2.0-flash

    Blame and responsibility

    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
    RegistryLite
    -0.59
     jaundice
    -0.50
     kaarangay
    -0.48
     Bathing
    -0.47
     Aph
    -0.47
     aph
    -0.47
    Rcpp
    -0.47
    tometer
    -0.47
     speeds
    -0.47
     <=",
    -0.47
    POSITIVE LOGITS
    WithMany
    0.64
     Vikipedi
    0.64
     responsibility
    0.63
     astore
    0.63
    fillType
    0.62
     Responsibility
    0.60
     responsabilité
    0.59
    IContainer
    0.58
     wireType
    0.58
     responsabilidad
    0.58
    Activations Density 0.684%

    No Known Activations