© 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. 4540
    Prev
    Next
    INDEX
    Explanations

    HTML tag attributes such as class and ID

    oai_token-act-pair · gemini-2.0-flash

    html code

    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
     nahilalakip
    -0.59
    ɵɵ
    -0.45
    ếng
    -0.44
    titleMargin
    -0.43
     NUKAT
    -0.43
    мка
    -0.41
    =$?
    -0.41
    DataMap
    -0.40
     palanca
    -0.40
    orec
    -0.40
    POSITIVE LOGITS
    
    0.82
    setVerticalGroup
    0.75
    migrationBuilder
    0.73
     تضيفلها
    0.71
     referenties
    0.69
    esez
    0.69
     мәкал
    0.68
    modelBuilder
    0.65
    ExecuteReader
    0.65
    AccessorTable
    0.63
    Activations Density 11.946%

    No Known Activations