© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 135501
    Prev
    Next
    INDEX
    Explanations

    late November

    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_1_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
    中
    0.85
    Don
    0.81
    的
    0.77
     *)
    0.75
    For
    0.75
    ません
    0.75
     Devil
    0.73
    |}
    0.72
     Depp
    0.72
    能
    0.72
    POSITIVE LOGITS
    いた
    1.52
     aujourd
    1.50
     isn
    1.35
    ला
    1.30
     doesn
    1.30
     березня
    1.21
    ই
    1.19
     он
    1.18
     आहेत
    1.13
    p
    1.12
    Activations Density 0.004%

    No Known Activations