© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8379
    Prev
    Next
    INDEX
    Explanations

    bracketed or quoted text that also contains numbers, punctuation, and whitespace.

    oai_token-act-pair · gemini-2.0-flash

    Punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    UnknownFieldSet
    -0.40
     س
    -0.38
     ز
    -0.33
     د
    -0.32
     م
    -0.31
     С
    -0.31
    ;'>
    -0.31
    )、
    -0.31
     К
    -0.30
    за
    -0.30
    POSITIVE LOGITS
    ########.
    0.67
    Autoritní
    0.63
    rungsseite
    0.61
    NUMX
    0.61
     Theſe
    0.56
     étoient
    0.55
     sanitaires
    0.54
     dieux
    0.53
     maternidade
    0.52
    قایناق‌لار
    0.52
    Activations Density 1.678%

    No Known Activations