© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10851
    Prev
    Next
    INDEX
    Explanations

    references to studies, grants and contracts

    oai_token-act-pair · gemini-2.0-flash

    research citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     onAnimation
    -0.77
    rrggbb
    -0.65
    GraphicsUnit
    -0.63
    archiviato
    -0.61
    getSeconds
    -0.60
    Géographie
    -0.59
     متعلقه
    -0.53
    帖最后由
    -0.52
     CascadeType
    -0.52
     setInterval
    -0.52
    POSITIVE LOGITS
    elser
    0.55
     Lordships
    0.55
    typeof
    0.52
    клопе
    0.52
    ValueStyle
    0.51
    govine
    0.51
    IMPORTED
    0.50
     logically
    0.49
    المشاركات
    0.49
     typeof
    0.48
    Activations Density 1.035%

    No Known Activations