© 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. 9080
    Prev
    Next
    INDEX
    Explanations

    programming collection methods

    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
     wars
    0.26
     aged
    0.25
     passion
    0.24
    nof
    0.24
     “
    0.24
     Cull
    0.23
     mere
    0.23
     overall
    0.23
     passions
    0.23
     explores
    0.23
    POSITIVE LOGITS
    芡
    0.27
     باکس
    0.26
    缀
    0.26
     Телефон
    0.26
    GORITHM
    0.26
    urit
    0.25
     Кай
    0.25
    ब्रुवारी
    0.25
     эффек
    0.25
     వెంటనే
    0.25
    Activations Density 0.053%

    No Known Activations