© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 30704
    Prev
    Next
    INDEX
    Explanations

    Following the order of operations

    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_40_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
     RAX
    0.31
    كتب
    0.29
     cinereo
    0.29
    klich
    0.28
    <unused84>
    0.28
     HNO
    0.28
    AAE
    0.28
     molécule
    0.28
    DIV
    0.27
     قبر
    0.27
    POSITIVE LOGITS
    𒌅
    0.32
    线性
    0.29
    信息
    0.29
    線性
    0.29
    ︽
    0.29
    鍙
    0.28
     정보를
    0.28
     Supper
    0.27
     जानकारी
    0.27
    是一
    0.27
    Activations Density 0.007%

    No Known Activations