© 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. 6148
    Prev
    Next
    INDEX
    Explanations

    words appearing in a list or enumeration

    oai_token-act-pair · gemini-2.0-flash

    multi-language tokens or mixed language content

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

    /

    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
     
    -0.87
    ,
    -0.79
    .
    -0.75
    '
    -0.73
    1
    -0.69
     -
    -0.68
    -
    -0.68
    3
    -0.68
    ’
    -0.67
     (
    -0.66
    POSITIVE LOGITS
    IntoConstraints
    1.62
    expandindo
    1.46
     виправивши
    1.43
     tartalomajánló
    1.42
     itſelf
    1.41
     Theſe
    1.41
     متعلقه
    1.40
    脚注の使い方
    1.37
     المعيارى
    1.36
     Мексичка
    1.32
    Activations Density 8.181%

    No Known Activations