© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205671
    Prev
    Next
    INDEX
    Explanations

    under the guise 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_6_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
     (
    0.81
    m
    0.75
    Co
    0.75
    q
    0.73
    ي
    0.71
    ES
    0.71
     of
    0.70
    he
    0.68
    es
    0.67
    i
    0.66
    POSITIVE LOGITS
     prenez
    0.80
    劶
    0.71
    hattim
    0.67
    "<
    0.64
    ЛЕ
    0.64
     开发
    0.63
    ány
    0.60
    ية
    0.60
     blacklist
    0.60
    ScriptBuf
    0.60
    Activations Density 0.001%

    No Known Activations