© 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
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91759
    Prev
    Next
    INDEX
    Explanations

    following lists or information

    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_11_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
     n
    0.79
     *
    0.68
     r
    0.67
     U
    0.67
     individuals
    0.65
     T
    0.64
     members
    0.63
     new
    0.63
     every
    0.60
     NIT
    0.60
    POSITIVE LOGITS
    存在する
    0.68
    コード
    0.68
    Routed
    0.68
    信頼
    0.67
    クエスト
    0.67
    又は
    0.66
    restaurant
    0.66
    BR
    0.65
    ḏ
    0.65
     جای
    0.65
    Activations Density 0.003%

    No Known Activations