© 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. 203829
    Prev
    Next
    INDEX
    Explanations

    0

    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
     ١
    0.48
     ۱
    0.39
     bảy
    0.39
     అరుణ
    0.38
    ABI
    0.38
    NEY
    0.38
     अमृतसर
    0.37
     समीप
    0.37
    ລິ
    0.37
     Apro
    0.37
    POSITIVE LOGITS
    –
    0.43
     –
    0.41
    wa
    0.39
     ’
    0.37
    ways
    0.36
     "
    0.35
    forced
    0.34
    opt
    0.33
    istasis
    0.33
    γα
    0.33
    Activations Density 0.001%

    No Known Activations