© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2628
    Prev
    Next
    INDEX
    Explanations

    young talent admiration

    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_39_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
    ＂
    0.39
     разом
    0.38
     sì
    0.37
    闢
    0.35
    砻
    0.35
     ইহা
    0.34
    කො
    0.34
     ″
    0.34
    のお客様
    0.34
    stir
    0.34
    POSITIVE LOGITS
     Poe
    0.42
     talent
    0.41
    根本
    0.39
     Jo
    0.39
    RADIUS
    0.38
    }^{*}=
    0.38
     दीक्षित
    0.38
     Inv
    0.38
     প্রতিভা
    0.37
     db
    0.37
    Activations Density 0.012%

    No Known Activations