© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4604
    Prev
    Next
    INDEX
    Explanations

    content related to image copyrights and permissions, especially in the context of the Canisius College Archives

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     approval
    -2.27
     Approval
    -2.19
     approved
    -2.03
    Approval
    -2.00
     approvals
    -1.97
     Approved
    -1.95
     approve
    -1.93
    approval
    -1.93
     approving
    -1.91
    Approved
    -1.88
    POSITIVE LOGITS
     per
    1.45
    per
    1.19
    Per
    1.13
     Per
    1.09
    PER
    0.95
     PER
    0.93
     percent
    0.66
    AsUp
    0.64
    writeFieldEnd
    0.56
     Roskov
    0.55
    Activations Density 1.860%

    No Known Activations