© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84646
    Prev
    Next
    INDEX
    Explanations

    loss calculation in code

    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_0_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
    ی
    2.72
    は
    2.19
    는
    2.05
    ים
    1.97
    ۔
    1.96
    ли
    1.73
    是
    1.67
    s
    1.65
    ের
    1.64
    یک
    1.63
    POSITIVE LOGITS
    '
    1.59
     on
    1.56
    AL
    1.29
    AN
    1.27
    ing
    1.25
    ↵
    1.23
    at
    1.21
     recogida
    1.18
    RI
    1.17
    IL
    1.16
    Activations Density 0.003%

    No Known Activations