© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11519
    Prev
    Next
    INDEX
    Explanations

    code related diffs, numbers, and file references.

    oai_token-act-pair · gemini-2.0-flash

    diverse non-English or specialized terms

    np_token-act-pair-logits · gpt-4o-mini

    identifiers and references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     
    -0.49
    kowitz
    -0.49
    nda
    -0.48
     radiators
    -0.48
    mi
    -0.46
     [
    -0.44
    kovsky
    -0.44
     constant
    -0.43
    金曜
    -0.43
    <b>
    -0.41
    POSITIVE LOGITS
    ագրություններ
    1.07
    Sucesor
    0.99
     חיצוניים
    0.97
    aarrggbb
    0.96
    expandindo
    0.92
    
    0.92
    PerformLayout
    0.88
     виправивши
    0.88
    parsedMessage
    0.84
     EconPapers
    0.82
    Activations Density 28.446%

    No Known Activations