© 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. 87588
    Prev
    Next
    INDEX
    Explanations

    measurements and data

    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
    ے۔
    0.45
    ED
    0.44
    </strong>
    0.42
    SR
    0.42
    <strong>
    0.41
    ET
    0.41
    SF
    0.40
    EDS
    0.40
    RY
    0.40
    mathrm
    0.38
    POSITIVE LOGITS
     m
    1.25
    м
    1.07
    m
    1.03
    م
    0.98
     м
    0.86
    ม
    0.84
     म
    0.80
    म
    0.76
    <0xA0>
    0.74
     n
    0.72
    Activations Density 0.000%

    No Known Activations