Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6343
    Prev
    Next
    INDEX
    Explanations

    names of people prefaced by titles or other symbols

    oai_token-act-pair · gemini-2.0-flash

    specific patterns and attributes in scientific descriptions

    np_token-act-pair-logits · gpt-4o-mini
    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
     виправивши
    -0.57
     autorytatywna
    -0.56
    ThroughAttribute
    -0.52
     surla
    -0.51
     hoạch
    -0.50
     JpaRepository
    -0.49
    invokeLater
    -0.48
    AutoScaleMode
    -0.46
     inclus
    -0.46
    AxisAlignment
    -0.45
    POSITIVE LOGITS
     AssemblyCulture
    0.58
    ătoare
    0.57
     sharpening
    0.53
     sharpen
    0.53
    τοι
    0.52
    [];
    
    0.51
    enite
    0.51
    lietta
    0.50
    CustomAttributes
    0.50
    [--
    0.50
    Activations Density 0.256%

    No Known Activations