© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88722
    Prev
    Next
    INDEX
    Explanations

    Decline Push-ups, dude ranch, appeal, DearMoon, SnakeGame, Ghostscript

    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_23_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
    າມ
    0.36
    Structural
    0.35
     minhas
    0.33
    边
    0.33
    坍
    0.33
     pouquinho
    0.32
    ımızı
    0.32
    크
    0.32
    𝗸
    0.32
    Ад
    0.32
    POSITIVE LOGITS
     இயற்க
    0.36
     Evers
    0.35
     संचालक
    0.35
     tato
    0.33
    uchtung
    0.33
    iffer
    0.32
     അടുത്ത
    0.32
     귀
    0.32
    fta
    0.31
    iculation
    0.31
    Activations Density 0.000%

    No Known Activations