© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 9665
    Prev
    Next
    INDEX
    Explanations

    numbers and statistical data

    oai_token-act-pair · gemini-2.0-flash

    mathematical symbols

    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
     myſelf
    -1.64
     للاسماء
    -1.52
     raiſ
    -1.52
     Efq
    -1.41
     itſelf
    -1.41
    RenderAtEndOf
    -1.34
     Мексичка
    -1.34
     purpoſe
    -1.34
    IntoConstraints
    -1.34
     ſeveral
    -1.32
    POSITIVE LOGITS
    ,
    1.09
    ↵↵
    0.99
    <eos>
    0.91
     
    0.90
    .
    0.85
     (
    0.85
    ↵
    0.84
     .
    0.76
    ;
    0.74
     ,
    0.71
    Activations Density 56.224%

    No Known Activations