© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 209668
    Prev
    Next
    INDEX
    Explanations

    letting go, letting her, letting it

    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_5_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
    os
    1.45
    un
    1.16
    с
    1.15
     philosopher
    1.11
    ul
    1.06
     collaborator
    1.06
     broadcaster
    1.05
    দের
    1.02
     counterpart
    1.02
    đena
    1.02
    POSITIVE LOGITS
    ;
    1.17
     a
    1.13
    ↵
    1.06
    }$
    1.00
    的选择
    0.99
    oo
    0.97
     at
    0.95
    M
    0.94
    atology
    0.93
    u
    0.91
    Activations Density 0.000%

    No Known Activations