© 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. 171101
    Prev
    Next
    INDEX
    Explanations

    have

    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
    “)
    0.35
    /}
    0.34
    ў
    0.34
     KN
    0.33
     পড়েন
    0.33
    ູ້
    0.32
    ಘ
    0.32
    )},
    0.32
    <0x82>
    0.31
    ,“
    0.31
    POSITIVE LOGITS
    ń
    0.55
    🅽
    0.50
     nul
    0.47
    𝒏
    0.46
    ncol
    0.45
    Ν
    0.42
    nta
    0.41
    Ŷ
    0.41
    nc
    0.41
    ntag
    0.41
    Activations Density 0.005%

    No Known Activations