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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10043
    Prev
    Next
    INDEX
    Explanations

    code documentation blocks

    oai_token-act-pair · gemini-2.0-flash

    Code and programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    writeFieldEnd
    -0.85
     للاسماء
    -0.81
    脚注の使い方
    -0.75
    
    -0.74
     ویکی‌پدیا
    -0.72
     Normdatei
    -0.71
     ligiloj
    -0.71
    migrationBuilder
    -0.71
     समीक्षाओं
    -0.69
     ब्रेकडाउन
    -0.69
    POSITIVE LOGITS
    Šaltiniai
    0.40
     assunto
    0.38
    jgl
    0.38
    sty
    0.37
     Compens
    0.37
     Comp
    0.36
    }}}}
    0.36
    FieldBuilder
    0.36
    гу
    0.35
    dur
    0.35
    Activations Density 1.389%

    No Known Activations