© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 57635
    Prev
    Next
    INDEX
    Explanations

    appear

    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_59_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     По
    0.56
    по
    0.45
    По
    0.40
     പോ
    0.36
    ایط
    0.35
    انیہ
    0.35
    ポ
    0.35
     포
    0.33
     Seems
    0.32
    heva
    0.32
    POSITIVE LOGITS
     appearing
    2.91
     appeared
    2.81
     appearance
    2.73
     apare
    2.66
     Appear
    2.63
     appear
    2.59
     Appearance
    2.56
    appearing
    2.48
    Appear
    2.45
    appear
    2.45
    Activations Density 0.164%

    No Known Activations