© 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. 13457
    Prev
    Next
    INDEX
    Explanations

    goal difference, points, or score

    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
    Not in Any Lists

    No Comments

    Negative Logits
     neph
    0.33
    ovalo
    0.32
    diam
    0.31
     tropomyosin
    0.31
    ड़ी
    0.30
    锲
    0.30
    Roz
    0.30
     Roz
    0.30
    годи
    0.30
    ropolis
    0.30
    POSITIVE LOGITS
    ด
    0.37
     给
    0.36
    ;
    0.36
    ER
    0.35
    元気
    0.34
    法国
    0.34
    er
    0.33
    AV
    0.33
    िड
    0.32
    法國
    0.31
    Activations Density 0.005%

    No Known Activations