© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 254026
    Prev
    Next
    INDEX
    Explanations

    espec

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    ंथ
    0.40
    сть
    0.36
     generally
    0.35
    generally
    0.35
     एनटी
    0.34
    z
    0.34
    訃
    0.34
    ㎎
    0.33
    বত
    0.33
     गुणनखंड
    0.33
    POSITIVE LOGITS
     specially
    1.65
    specially
    1.47
     spécialement
    1.32
     Spec
    1.30
    Spec
    1.20
     специально
    1.12
     spec
    1.11
     espec
    1.01
    spec
    1.01
    特
    1.01
    Activations Density 0.000%

    No Known Activations