© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 197825
    Prev
    Next
    INDEX
    Explanations

    digging hole, diggy hole

    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_12_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
    G
    0.64
     Pltf
    0.61
    R
    0.60
     Woodland
    0.57
     Wolves
    0.56
     woodland
    0.56
    Ron
    0.55
    GUND
    0.55
    Newline
    0.54
    र
    0.54
    POSITIVE LOGITS
    ie
    0.50
    idi
    0.50
     डालेंगे
    0.48
    aka
    0.48
    ixer
    0.47
    ine
    0.46
     сложно
    0.46
     замо
    0.45
    ור
    0.45
    호를
    0.44
    Activations Density 0.000%

    No Known Activations