© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199627
    Prev
    Next
    INDEX
    Explanations

    English and non-English words

    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
    是否
    0.32
     প্রকাশের
    0.31
    Left
    0.30
    reve
    0.30
     அவர்களின்
    0.30
    添加
    0.29
     ಪ
    0.29
     அவர்கள்
    0.29
     কিভাবে
    0.29
    作成
    0.29
    POSITIVE LOGITS
    ципа
    0.32
     міні
    0.30
    getRow
    0.30
    +_
    0.29
    શિ
    0.29
    ків
    0.28
    qli
    0.28
     intér
    0.28
     estadio
    0.28
    ស៊ី
    0.28
    Activations Density 0.001%

    No Known Activations