© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 155657
    Prev
    Next
    INDEX
    Explanations

    narrative opening phrases

    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_60_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
     частью
    0.46
     часть
    0.39
     //-
    0.38
     My
    0.38
     /\
    0.38
    很久
    0.37
     veer
    0.36
                         
    0.35
     część
    0.35
     part
    0.35
    POSITIVE LOGITS
    ‘
    0.59
    It
    0.57
    ’
    0.57
     sure
    0.54
    '
    0.53
    Out
    0.52
    <strong>
    0.51
     will
    0.50
    </em>
    0.50
     It
    0.50
    Activations Density 0.000%

    No Known Activations