© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14178
    Prev
    Next
    INDEX
    Explanations

    code, scientific language, and email addresses

    oai_token-act-pair · gemini-2.0-flash

    call

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     مشين
    -0.93
    AndEndTag
    -0.85
    addCriterion
    -0.65
    AutoresizingMask
    -0.62
    AxisAlignment
    -0.61
    setVerticalGroup
    -0.61
    ajuato
    -0.60
     getItemCount
    -0.58
     bVar
    -0.57
     compositor
    -0.57
    POSITIVE LOGITS
    <bos>
    0.55
    ్రామ
    0.50
    upe
    0.43
     counted
    0.42
    Begriffsklä
    0.41
     ahead
    0.40
     advanced
    0.40
    냅
    0.40
    Ahead
    0.39
    WebVitals
    0.39
    Activations Density 4.297%

    No Known Activations