© 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. 24803
    Prev
    Next
    INDEX
    Explanations

    river

    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
     River
    0.88
    River
    0.87
     RIVER
    0.84
     river
    0.84
    river
    0.79
    河
    0.75
     rivers
    0.73
     Rivers
    0.66
     नदी
    0.62
    rivers
    0.62
    POSITIVE LOGITS
     valley
    0.79
    basin
    0.63
     basin
    0.63
    bed
    0.63
     Valley
    0.60
    谷
    0.59
    valley
    0.58
    beds
    0.57
    Valley
    0.57
     Basin
    0.57
    Activations Density 0.080%

    No Known Activations