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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14500
    Prev
    Next
    INDEX
    Explanations

    place names and location-related words, often in the context of sports

    oai_token-act-pair · gemini-2.0-flash

    stadiums/games

    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
    __":
    -0.63
    __":
    -0.61
    :✨
    -0.59
    bootstrapcdn
    -0.56
    __':
    -0.56
     resourceCulture
    -0.55
    RoutingModule
    -0.51
     JpaRepository
    -0.51
    yntaxException
    -0.50
    nloa
    -0.50
    POSITIVE LOGITS
    цездатний
    0.65
    findOrFail
    0.52
     وتسجيلات
    0.49
     Roanoke
    0.47
     Schenectady
    0.47
    Phaser
    0.46
     Coli
    0.46
    INSEE
    0.46
     DevExpress
    0.45
     Италијани
    0.45
    Activations Density 1.859%

    No Known Activations