Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 16-GEMMASCOPE-TRANSCODER-16K
    4. 1132
    Prev
    Next
    INDEX
    Explanations

    numerical data or labels in study type documents

    oai_token-act-pair · gemini-2.0-flash

    unclear

    np_token-act-pair-logits · gemini-2.0-flash

    percentages and ratios

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.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
    MigrationBuilder
    -1.01
    StoryboardSegue
    -0.86
    yntaxException
    -0.74
    LookAnd
    -0.70
    posedge
    -0.69
    eait
    -0.69
     pngtree
    -0.68
     ContentValues
    -0.65
     Monfieur
    -0.64
    зулта
    -0.64
    POSITIVE LOGITS
    例文帳に追加
    0.44
    scalatest
    0.41
    PRNewswire
    0.40
    rungsseite
    0.40
    setVerticalGroup
    0.39
    コース
    0.36
     rushed
    0.35
     attacc
    0.35
     organic
    0.35
     teki
    0.34
    Activations Density 13.682%

    No Known Activations