© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130672
    Prev
    Next
    INDEX
    Explanations

    down-regulated genes

    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_1_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
    p
    1.57
    ک
    1.39
    st
    1.37
    of
    1.25
    ව
    1.21
    ن
    1.19
    ק
    1.16
    न
    1.11
    the
    1.08
    ص
    1.07
    POSITIVE LOGITS
     I
    1.40
    U
    1.13
     in
    1.03
     U
    1.00
     MS
    0.96
     II
    0.94
     Wi
    0.94
     K
    0.89
     About
    0.88
     IM
    0.88
    Activations Density 0.011%

    No Known Activations