© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    4. 64505
    Prev
    Next
    INDEX
    Explanations

    code blocks

    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_41_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
    Laut
    0.40
    getID
    0.40
     loudest
    0.40
     XP
    0.39
    ومة
    0.38
     옳
    0.37
    INFE
    0.36
     valley
    0.36
     getLocation
    0.36
     papal
    0.36
    POSITIVE LOGITS
    ذي
    0.39
     communicated
    0.37
    神経
    0.36
    չ
    0.36
    散射
    0.35
     demonstrated
    0.34
     Vita
    0.34
    惟
    0.34
    ớt
    0.34
     distract
    0.34
    Activations Density 0.003%

    No Known Activations