© 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. 33331
    Prev
    Next
    INDEX
    Explanations

    weak, small, low, half

    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
    ت
    0.89
    ای
    0.81
     in
    0.79
    т
    0.78
    ט
    0.73
     hypothes
    0.70
    ین
    0.70
    0
    0.69
    8
    0.68
    да
    0.68
    POSITIVE LOGITS
    0.70
    ?
    0.70
    S
    0.60
    therly
    0.58
    rington
    0.57
    리
    0.57
    䈉
    0.57
    sement
    0.56
    plaats
    0.56
     Annals
    0.55
    Activations Density 0.000%

    No Known Activations