© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 194288
    Prev
    Next
    INDEX
    Explanations

    Times New Roman

    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_15_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
     ماس
    0.54
     masu
    0.53
    Transaction
    0.52
     сал
    0.52
     노
    0.52
    ⿳
    0.51
     noh
    0.51
     страхо
    0.50
    脯
    0.50
    บวน
    0.49
    POSITIVE LOGITS
    રે
    0.56
     from
    0.51
    ről
    0.50
     Leia
    0.50
     FROM
    0.49
     quelle
    0.48
     żeby
    0.47
    큽
    0.46
     shit
    0.46
     diesen
    0.46
    Activations Density 0.001%

    No Known Activations