© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 257
    Prev
    Next
    INDEX
    Explanations

    code snippets and code-related words (e.g. names of functions, objects etc.) in various programming languages

    oai_token-act-pair · gemini-2.0-flash

    code punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    cheibe
    -0.40
     marka
    -0.40
    ={`/
    -0.37
     sample
    -0.35
     ſtate
    -0.34
    zter
    -0.34
    Breakdown
    -0.33
     Daß
    -0.33
     ftate
    -0.33
    Transcription
    -0.32
    POSITIVE LOGITS
    <bos>
    1.20
     дописавши
    0.85
    oredCriteria
    0.78
     вікі
    0.70
    expandindo
    0.68
    
    0.67
    存于互联网档案馆
    0.66
    AnchorStyles
    0.65
     مشين
    0.63
    Autoritní
    0.63
    Activations Density 58.211%

    No Known Activations