© 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-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164854
    Prev
    Next
    INDEX
    Explanations

    parentheses and programming code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ing
    0.38
     interrog
    0.38
     annot
    0.34
     comprom
    0.34
    .
    0.30
     viol
    0.30
     answering
    0.30
     utens
    0.30
     interpre
    0.30
     propon
    0.29
    POSITIVE LOGITS
    crazy
    0.35
    疯狂
    0.34
     hectic
    0.33
     crazy
    0.33
    䄪
    0.32
    ارم
    0.31
     م
    0.30
    த்த
    0.30
    بینی
    0.30
    佸
    0.30
    Activations Density 0.058%

    No Known Activations