© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 69371
    Prev
    Next
    INDEX
    Explanations

    organizations and education

    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_46_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
     H
    1.75
     h
    1.35
    H
    1.33
     اله
    1.16
     হ
    1.07
     ه
    1.06
     ہ
    1.02
     एच
    1.02
     ह
    1.00
    Ｈ
    1.00
    POSITIVE LOGITS
    েশ্বর
    0.41
    Champ
    0.40
     Шев
    0.39
     Bow
    0.39
    ******
    0.38
    Bow
    0.38
    者
    0.37
     ше
    0.37
    θαν
    0.36
    whe
    0.36
    Activations Density 0.052%

    No Known Activations