© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9367
    Prev
    Next
    INDEX
    Explanations

    section enumerations such as (i), (ii), (a), (b), or (c)

    oai_token-act-pair · gemini-2.0-flash

    parenthesis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     weights
    -0.46
    AsUp
    -0.46
     synch
    -0.43
     Urbano
    -0.43
    EventId
    -0.43
     Gusto
    -0.42
     nameof
    -0.42
     foils
    -0.41
     часу
    -0.40
     craw
    -0.40
    POSITIVE LOGITS
    出版年
    0.74
    MENAFN
    0.57
    aa
    0.57
     Wikimédia
    0.56
     GenerationType
    0.56
    Explanation
    0.55
    migrationBuilder
    0.54
    bA
    0.54
    Expedia
    0.53
     TextAppearance
    0.52
    Activations Density 8.027%

    No Known Activations