© 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. 1230
    Prev
    Next
    INDEX
    Explanations

    a mix of Russian and English code-related terms, possibly identifying questions or instructions in a technical context.

    oai_token-act-pair · 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
    neſs
    -1.02
     Majefty
    -1.00
    ſelf
    -0.79
    NUMX
    -0.75
     Jefus
    -0.74
     Efq
    -0.73
     greateſt
    -0.70
     iconFacebook
    -0.68
    ^(@)
    -0.68
     purpoſe
    -0.68
    POSITIVE LOGITS
    loem
    0.72
     '\\;'
    0.71
    openConnection
    0.66
     Wrangler
    0.66
    AddHtmlAttribute
    0.66
     EClass
    0.65
    bootstrapcdn
    0.63
    esgue
    0.63
    ésil
    0.63
    beiter
    0.62
    Activations Density 7.512%

    No Known Activations