© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 253801
    Prev
    Next
    INDEX
    Explanations

    language symbols

    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_56_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
     ????
    0.53
     ג
    0.51
     "????
    0.50
     Ф
    0.48
     中
    0.46
     へ
    0.46
     ח
    0.45
     山
    0.44
    ????
    0.44
     แ
    0.43
    POSITIVE LOGITS
    အပိုင်း
    0.47
    ❞
    0.46
     करीत
    0.44
    ONEDB
    0.43
    ः
    0.43
    ​]]
    0.43
     यूक
    0.42
     Ausstattung
    0.42
    CHINA
    0.42
    ंध्र
    0.42
    Activations Density 0.015%

    No Known Activations