© 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. 75114
    Prev
    Next
    INDEX
    Explanations

    other or important

    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
     యా
    0.33
     ಏನು
    0.29
    msubsup
    0.29
     whats
    0.27
     what
    0.26
     terbesar
    0.26
     Ac
    0.26
    &#
    0.26
     Armin
    0.26
     Ja
    0.25
    POSITIVE LOGITS
     particip
    0.29
    ニーカー
    0.29
     રાજ્ય
    0.28
     بھول
    0.28
    شاركة
    0.28
    த்துடன்
    0.27
    商品の
    0.27
     lotions
    0.27
    ுடன்
    0.26
    酩
    0.26
    Activations Density 0.002%

    No Known Activations