© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    4. 59683
    Prev
    Next
    INDEX
    Explanations

    back of his hand

    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
    ent
    0.53
    et
    0.47
    国际
    0.44
     familiale
    0.42
    國際
    0.40
    y
    0.40
    en
    0.40
     العالمية
    0.40
    enov
    0.39
     Ukraine
    0.39
    POSITIVE LOGITS
    کلی
    0.42
    ʙ
    0.41
    ジョン
    0.41
    챌
    0.41
    awal
    0.40
     effic
    0.40
     dices
    0.40
     ऊंचा
    0.39
     There
    0.38
    کام
    0.38
    Activations Density 0.003%

    No Known Activations