© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3825
    Prev
    Next
    INDEX
    Explanations

    multiple numbers inside larger text and parentheses

    oai_token-act-pair · gemini-2.0-flash

    diverse geographical terms

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

    place names

    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
     Theſe
    -0.85
     myſelf
    -0.83
     Monfieur
    -0.81
     themſelves
    -0.74
     Anſ
    -0.72
     Beſ
    -0.72
     Inſ
    -0.71
    ſelf
    -0.71
     auffi
    -0.70
     uſe
    -0.69
    POSITIVE LOGITS
    achusetts
    0.57
    脚注の使い方
    0.50
    caloosa
    0.46
    lawayo
    0.46
     F
    0.45
    мость
    0.45
    restes
    0.44
    komme
    0.44
    انیا
    0.44
    丁目
    0.43
    Activations Density 1.058%

    No Known Activations