© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84632
    Prev
    Next
    INDEX
    Explanations

    explanation, please provide

    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_23_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
    強度
    0.29
    $=
    0.28
    $=\
    0.28
     AGENCY
    0.26
    라도
    0.25
    निज
    0.25
    ܤ
    0.24
     GAMES
    0.24
    NETWORK
    0.24
    ską
    0.24
    POSITIVE LOGITS
     Clinton
    0.29
     Voyage
    0.26
     более
    0.25
     Islam
    0.24
     Ꭰ
    0.23
    yland
    0.23
     vertically
    0.23
     Print
    0.22
     carpet
    0.22
    ிகளுக்கு
    0.22
    Activations Density 0.011%

    No Known Activations