© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17386
    Prev
    Next
    INDEX
    Explanations

    assume Output

    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_40_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
     참여
    0.46
    *{
    0.42
    ^*
    0.41
     participated
    0.41
    {-
    0.40
    ^-
    0.40
    했을
    0.38
     *>
    0.37
    $-$
    0.37
     پوس
    0.37
    POSITIVE LOGITS
     অভিনেত্র
    0.40
    تام
    0.38
    สดง
    0.38
    ുന്നത്
    0.37
    නම්
    0.37
     hypoallergenic
    0.37
    çando
    0.36
    Simone
    0.36
    yllic
    0.36
    цвет
    0.36
    Activations Density 0.002%

    No Known Activations