© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 211832
    Prev
    Next
    INDEX
    Explanations

    leather items

    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_20_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
     kills
    0.44
     impractic
    0.42
     sizes
    0.41
     decreases
    0.38
     killing
    0.38
     ኣ
    0.37
     sweeps
    0.36
     கொலை
    0.36
     lehetős
    0.36
     size
    0.35
    POSITIVE LOGITS
    fox
    0.35
    democracy
    0.33
    )}
    0.31
    his
    0.31
     البح
    0.31
    ow
    0.31
    ксана
    0.31
    Driver
    0.30
    Flex
    0.30
    veri
    0.30
    Activations Density 0.001%

    No Known Activations