© 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. 10016
    Prev
    Next
    INDEX
    Explanations

    Flash video related Javascript code snippets

    oai_token-act-pair · 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
     الحره
    -0.93
    
    -0.84
    EDEFAULT
    -0.84
     propOrder
    -0.77
    __*/
    -0.74
    NameInMap
    -0.73
    SequentialGroup
    -0.71
    انجليز
    -0.68
     مرئيه
    -0.67
     समीक्षाओं
    -0.66
    POSITIVE LOGITS
    Real
    0.62
     Real
    0.59
    real
    0.56
     real
    0.52
    rome
    0.45
     mul
    0.43
    wts
    0.42
    Shock
    0.42
    ="#"><
    0.41
    باع
    0.41
    Activations Density 1.215%

    No Known Activations