© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 76906
    Prev
    Next
    INDEX
    Explanations

    distribution

    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_53_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
     കേന്ദ്ര
    0.43
     Ban
    0.38
    ณ์
    0.37
     midline
    0.36
    ]$-
    0.36
    Ban
    0.35
     కేంద్ర
    0.35
    ঙ্গের
    0.35
    飥
    0.35
    <0x9E>
    0.35
    POSITIVE LOGITS
     dist
    1.31
    Dist
    1.09
    dist
    1.07
     Dist
    1.02
    DIST
    0.88
     DIST
    0.88
     distro
    0.74
     Distortion
    0.66
     Distributors
    0.63
     st
    0.62
    Activations Density 0.006%

    No Known Activations