© 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. 3866
    Prev
    Next
    INDEX
    Explanations

    legal and/or scientific writing conventions, including proper nouns, dates, and measurement qualifiers in scientific writing

    oai_token-act-pair · gemini-2.0-flash

    State changes or completions

    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
     developed
    -0.66
    Developed
    -0.59
     lit
    -0.59
     Developed
    -0.58
     finished
    -0.54
    developed
    -0.53
     développé
    -0.53
    ArgsConstructor
    -0.52
     démarrer
    -0.52
     opening
    -0.51
    POSITIVE LOGITS
     Collected
    0.61
    SharedCtor
    0.55
    Captured
    0.55
     sucked
    0.53
    HasOne
    0.53
    Saved
    0.53
     toege
    0.52
     Saved
    0.52
     killed
    0.51
     assassinated
    0.51
    Activations Density 9.147%

    No Known Activations