© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3674
    Prev
    Next
    INDEX
    Explanations

    mentions of animals and their habitats and breeding, especially birds

    oai_token-act-pair · gemini-2.0-flash

    Bird breeding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    brecht
    -0.50
     ivelany
    -0.48
    umont
    -0.48
    ReusableCell
    -0.47
     Blvd
    -0.47
     both
    -0.46
     saison
    -0.46
     BoxFit
    -0.43
    dalena
    -0.43
    ctu
    -0.43
    POSITIVE LOGITS
     snippetHide
    0.63
     snoring
    0.60
     <<<<<<<<<<<<<<
    0.59
    MigrationBuilder
    0.56
     Мексичка
    0.56
    atória
    0.55
    ніципалі
    0.55
    ⓧ
    0.54
    createServer
    0.54
     defaultstate
    0.54
    Activations Density 16.951%

    No Known Activations