© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53540
    Prev
    Next
    INDEX
    Explanations

    key-value separator

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    ς
    0.44
     Truth
    0.41
     व्हायर
    0.41
    ресень
    0.39
    ＝
    0.38
    Truth
    0.38
    〜
    0.38
    ＞
    0.37
     $=$
    0.37
     INCIDENTAL
    0.36
    POSITIVE LOGITS
     "",
    0.70
     "\
    0.57
     ".",
    0.55
     "";
    0.54
     "-",
    0.54
    "",
    0.54
     "+
    0.52
     "|
    0.51
     "**
    0.50
     "["
    0.49
    Activations Density 0.005%

    No Known Activations