© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18164
    Prev
    Next
    INDEX
    Explanations

    official documentation

    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_40_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
    喵
    0.39
    暊
    0.38
    ervo
    0.38
     newspapers
    0.36
     Procedures
    0.36
    解答
    0.35
    期刊
    0.35
     Rules
    0.34
    孭
    0.33
     বাঙাল
    0.33
    POSITIVE LOGITS
     official
    1.86
     официа
    1.75
     Official
    1.68
    Official
    1.67
    官方
    1.66
     oficial
    1.63
    official
    1.59
     ufficiale
    1.52
     OFFICIAL
    1.48
     officially
    1.46
    Activations Density 0.022%

    No Known Activations