© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40573
    Prev
    Next
    INDEX
    Explanations

    end of project report

    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_3_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
    proj
    0.62
     DKI
    0.59
     проек
    0.58
    of
    0.58
    ከላከ
    0.57
     proyecto
    0.57
    jecture
    0.57
    +\
    0.56
    have
    0.56
     projections
    0.56
    POSITIVE LOGITS
    েন
    0.62
    ü
    0.61
    ർ
    0.61
     a
    0.60
    ר
    0.58
    ن
    0.57
    ind
    0.57
    a
    0.56
    ஸ்
    0.56
     री
    0.55
    Activations Density 0.003%

    No Known Activations