© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79607
    Prev
    Next
    INDEX
    Explanations

    mixing ingredients in a bowl

    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_31_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
     Mindfulness
    0.44
    禅
    0.43
     Meditation
    0.40
     bhikkhu
    0.38
    不成
    0.38
    drawiam
    0.36
     piped
    0.36
    💛
    0.35
     scrolls
    0.35
    zerel
    0.35
    POSITIVE LOGITS
     delirium
    0.38
     detergent
    0.36
    ર્ચ
    0.36
    deter
    0.35
     sharply
    0.35
     cael
    0.35
     міні
    0.34
    %%%%%%%%
    0.34
     craters
    0.34
     लास्ट
    0.33
    Activations Density 0.030%

    No Known Activations