© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35692
    Prev
    Next
    INDEX
    Explanations

    Here's a breakdown

    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_31_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
    совой
    0.35
     منتشر
    0.35
    Favor
    0.33
     fill
    0.33
    ि
    0.33
     favor
    0.33
    favor
    0.32
     ws
    0.32
     wears
    0.32
     Favor
    0.32
    POSITIVE LOGITS
     എന്നു
    0.38
     plabic
    0.37
    uatan
    0.35
    Ге
    0.34
    😂
    0.34
    -__
    0.33
    ⅜
    0.33
    uding
    0.33
     กู
    0.33
     diput
    0.33
    Activations Density 0.056%

    No Known Activations