© 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. 47975
    Prev
    Next
    INDEX
    Explanations

    code start marker

    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
    focusable
    0.16
    ;%%
    0.16
    centerY
    0.16
    opies
    0.16
    ◥
    0.16
    粪
    0.15
    juvant
    0.15
    bibinfo
    0.15
    zuf
    0.14
    pyridine
    0.14
    POSITIVE LOGITS
     rotate
    0.17
     rotated
    0.16
    rotate
    0.15
     Western
    0.15
     .
    0.14
    ᱟ
    0.14
     string
    0.14
     spear
    0.14
     Rotate
    0.14
     bunnies
    0.14
    Activations Density 0.060%

    No Known Activations