© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199499
    Prev
    Next
    INDEX
    Explanations

    photo ID or driver's license

    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_12_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
    owns
    0.44
     l
    0.43
    at
    0.41
    ua
    0.40
    marine
    0.39
    or
    0.39
    il
    0.39
    over
    0.39
    ist
    0.39
    L
    0.38
    POSITIVE LOGITS
     медве
    0.38
    吔
    0.36
     vencedor
    0.35
     উইকেট
    0.35
     humild
    0.35
     šta
    0.34
     CYAN
    0.34
     diligently
    0.34
     readFile
    0.34
     അനുവദ
    0.34
    Activations Density 0.000%

    No Known Activations