© 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-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11118
    Prev
    Next
    INDEX
    Explanations

    purpose or consequence of

    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
    in
    0.52
     Schuyler
    0.45
    T
    0.45
    :")
    0.44
    S
    0.43
    াজী
    0.43
     архівної
    0.42
     കഴിയ
    0.41
    ra
    0.41
     Bowen
    0.41
    POSITIVE LOGITS
    FindFileData
    0.46
    Asalamualaikum
    0.46
    बीटी
    0.46
    दय
    0.45
     اكتوبر
    0.45
     litigants
    0.45
    ^{
    0.44
    当
    0.44
    ^{\
    0.44
    人不
    0.44
    Activations Density 0.058%

    No Known Activations