© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 25020
    Prev
    Next
    INDEX
    Explanations

    all

    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_56_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
     an
    0.42
    works
    0.35
     "!
    0.35
    帳
    0.35
     nared
    0.34
     "_
    0.34
    abcdef
    0.34
     '_
    0.33
    জিৎ
    0.33
     "¿
    0.33
    POSITIVE LOGITS
     pur
    0.53
    Pur
    0.48
     thing
    0.47
     purifier
    0.46
     Pur
    0.46
     PUR
    0.44
    asing
    0.42
    pur
    0.42
     else
    0.42
    ancing
    0.40
    Activations Density 0.002%

    No Known Activations