© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 37040
    Prev
    Next
    INDEX
    Explanations

    information is

    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
    Negative Logits
    지금
    0.35
     ricerc
    0.34
     지금
    0.34
     bifurcation
    0.34
    🛠
    0.34
    ENDO
    0.34
    ئيه
    0.33
    䡏
    0.33
     specs
    0.32
     resources
    0.32
    POSITIVE LOGITS
    த்துக்கும்
    0.35
    oll
    0.35
    暴露
    0.34
     sm
    0.33
    div
    0.33
    巨
    0.33
    over
    0.32
    hint
    0.32
    removeAll
    0.32
    liberal
    0.32
    Activations Density 0.002%

    No Known Activations