© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    4. 66553
    Prev
    Next
    INDEX
    Explanations

    code additions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    icija
    0.39
    >(
    0.39
    強化
    0.38
    เสริม
    0.38
    샬
    0.37
    usto
    0.37
     sei
    0.36
    BackgroundColor
    0.36
    óstico
    0.35
    Ⴚ
    0.35
    POSITIVE LOGITS
    橑
    0.43
     pater
    0.40
    Expend
    0.40
     expenditure
    0.39
     withdrawing
    0.39
     Expenditure
    0.39
    கோ
    0.38
     Inheritance
    0.37
     consuming
    0.37
    ভে
    0.37
    Activations Density 0.000%

    No Known Activations