© 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. 155682
    Prev
    Next
    INDEX
    Explanations

    unt

    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
    <0xAD>
    0.59
     Title
    0.55
     IT
    0.54
     tête
    0.54
     Text
    0.54
     тот
    0.53
     టై
    0.53
     ti
    0.52
    ྟ
    0.52
     టీ
    0.52
    POSITIVE LOGITS
     luminance
    0.39
    的应用
    0.35
    名为
    0.34
    పీ
    0.34
     pengguna
    0.34
     mahdoll
    0.34
    <0x96>
    0.34
    名叫
    0.34
     awareness
    0.34
     erfolgen
    0.34
    Activations Density 0.027%

    No Known Activations