© 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. 127689
    Prev
    Next
    INDEX
    Explanations

    comprehension and topics

    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
    Not in Any Lists

    No Comments

    Negative Logits
    (
    0.80
     repayment
    0.66
     interview
    0.66
     it
    0.65
     ZX
    0.65
     escalator
    0.63
     WV
    0.63
     opinion
    0.61
     entertainment
    0.61
     nightlife
    0.60
    POSITIVE LOGITS
    ת
    1.02
    م
    0.93
    ت
    0.92
    ع
    0.92
    v
    0.89
    ج
    0.87
    ات
    0.85
    m
    0.84
    يش
    0.83
    ק
    0.83
    Activations Density 0.000%

    No Known Activations