© 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. 215242
    Prev
    Next
    INDEX
    Explanations

    rumors of

    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
     potential
    0.33
     Potential
    0.32
     proposals
    0.31
     conv
    0.31
     Congress
    0.31
     Proposals
    0.31
     "+"
    0.30
     dân
    0.29
    footed
    0.29
     "+
    0.29
    POSITIVE LOGITS
    失敗
    0.38
     실패
    0.33
    عبير
    0.33
     دچار
    0.31
     እንዳ
    0.30
     sufrir
    0.30
     mistrust
    0.30
    istir
    0.29
     syukur
    0.29
    苦手
    0.29
    Activations Density 0.002%

    No Known Activations