© 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. 313
    Prev
    Next
    INDEX
    Explanations

    code snippets involving parentheses or function calls

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    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
    //
    -0.47
     bArr
    -0.46
     Serbian
    -0.46
    gradle
    -0.46
    otoxin
    -0.45
     jLabel
    -0.45
    iformis
    -0.43
     Bosnia
    -0.43
    krie
    -0.43
    BlockingQueue
    -0.43
    POSITIVE LOGITS
    })->
    0.71
    extAlignment
    0.69
    Santis
    0.69
     betweenstory
    0.68
     wireType
    0.65
     NSCoder
    0.65
    AndEndTag
    0.63
    GraphicsUnit
    0.63
     محفوظة
    0.62
     />";
    0.62
    Activations Density 3.435%

    No Known Activations