© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 902
    Prev
    Next
    INDEX
    Explanations

    verbs describing mental or emotional states

    oai_token-act-pair · gemini-2.0-flash

    Surprise/strong feelings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     bezeichneter
    -0.64
     الحره
    -0.63
    esgue
    -0.62
     Tangerang
    -0.60
    Демографія
    -0.60
    ensible
    -0.59
    σιμοποι
    -0.58
    FunctionFlags
    -0.56
    StoryboardSegue
    -0.55
    inematic
    -0.55
    POSITIVE LOGITS
     us
    0.76
     me
    0.66
    AddField
    0.60
     MediatR
    0.59
    AntiForgeryToken
    0.59
    internalType
    0.58
    DeleteBehavior
    0.56
     dotato
    0.56
     him
    0.54
     Superhosts
    0.52
    Activations Density 2.788%

    No Known Activations