© 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. 203781
    Prev
    Next
    INDEX
    Explanations

    cricket pitch

    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
     XI
    0.51
     eleven
    0.47
     Eleven
    0.44
     Football
    0.43
    XI
    0.43
     XIII
    0.42
     XV
    0.40
    Ⅺ
    0.40
     DV
    0.39
    Eleven
    0.39
    POSITIVE LOGITS
     Pitch
    0.60
    Board
    0.58
    Pitch
    0.57
     Board
    0.54
     pitch
    0.53
    pitch
    0.49
     बोर्ड
    0.43
    originally
    0.42
     Pak
    0.41
     originally
    0.40
    Activations Density 0.000%

    No Known Activations