© 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. 127983
    Prev
    Next
    INDEX
    Explanations

    today

    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
    Negative Logits
    เป็น
    0.79
    ﻝ
    0.76
     eyelids
    0.70
    ﺟ
    0.69
    ﻳ
    0.66
     Έ
    0.66
    ни
    0.65
    ע
    0.65
     распростран
    0.64
     interesantes
    0.64
    POSITIVE LOGITS
    o
    1.00
    a
    0.91
    h
    0.91
    w
    0.89
    7
    0.86
    u
    0.80
    8
    0.77
     heutigen
    0.76
    e
    0.75
    f
    0.74
    Activations Density 0.000%

    No Known Activations