© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19819
    Prev
    Next
    INDEX
    Explanations

    script and style tags

    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_15_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
    Leod
    0.43
     Monday
    0.41
    seconds
    0.41
    ow
    0.41
    ול
    0.41
    one
    0.40
    </h4>
    0.39
    দ্বার
    0.39
     Clyde
    0.38
    ou
    0.38
    POSITIVE LOGITS
     옷
    0.46
     життя
    0.44
     আশ্রম
    0.41
    рома
    0.40
    BadRequest
    0.40
    ρου
    0.40
    槳
    0.40
     кафе
    0.40
     акысыз
    0.40
    лет
    0.39
    Activations Density 0.005%

    No Known Activations