© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 62674
    Prev
    Next
    INDEX
    Explanations

    advantage over

    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_2_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
     colabor
    0.89
    ,
    0.84
    н
    0.82
    ли
    0.81
    ట్లు
    0.80
    CurrentImageData
    0.80
     pone
    0.79
     можа
    0.76
     veio
    0.76
    רה
    0.75
    POSITIVE LOGITS
     on
    1.30
    >
    1.17
    ین
    1.09
    बी
    1.01
    ুনের
    1.01
    re
    1.00
    )
    1.00
     in
    0.99
    5
    0.99
    The
    0.97
    Activations Density 0.004%

    No Known Activations