© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 27-GEMMASCOPE-2-TRANSCODER-262K
    4. 196632
    Prev
    Next
    INDEX
    Explanations

    es

    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_27_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
    াদেশিক
    0.39
    ۶
    0.38
    <unused409>
    0.38
    شش
    0.38
     giugno
    0.38
    osur
    0.38
     degener
    0.37
    챠
    0.36
    Ell
    0.36
     derives
    0.35
    POSITIVE LOGITS
     ,
    0.40
     /
    0.38
     ((
    0.38
    行
    0.34
     ,
    0.33
    ԝ
    0.33
     ،
    0.32
     Impression
    0.32
    上次
    0.32
    /(
    0.32
    Activations Density 0.006%

    No Known Activations