© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87858
    Prev
    Next
    INDEX
    Explanations

    names and Chinese/Korean characters

    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_3_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
    ;
    0.76
    ﻒ
    0.65
    ’।
    0.64
    н
    0.63
    ;",
    0.63
     {};
    0.61
    recognized
    0.61
    лябин
    0.60
    იღ
    0.59
    ≙
    0.59
    POSITIVE LOGITS
    on
    0.76
    ens
    0.69
    ishing
    0.63
    u
    0.63
    able
    0.62
    ant
    0.61
     Il
    0.59
     on
    0.58
     It
    0.58
     Bill
    0.58
    Activations Density 0.000%

    No Known Activations