© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 201272
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ig
    1.08
    on
    1.05
    in
    1.00
    ol
    0.95
    ิตย์
    0.89
    ف
    0.89
     spacers
    0.88
     royals
    0.86
    IN
    0.84
     y
    0.82
    POSITIVE LOGITS
    ne
    1.06
    не
    0.99
    ắt
    0.95
    ﻤ
    0.89
    ă
    0.89
    ние
    0.88
    ﺎ
    0.87
    𝘢
    0.86
    时间和
    0.85
    ﻜ
    0.84
    Activations Density 0.000%

    No Known Activations