© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 69603
    Prev
    Next
    INDEX
    Explanations

    Long

    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_46_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
    With
    0.54
     With
    0.48
    Progress
    0.48
     Progress
    0.47
    From
    0.44
     It
    0.43
     Recipes
    0.42
     Composition
    0.42
    "
    0.42
     "
    0.41
    POSITIVE LOGITS
     谢
    0.47
    KET
    0.38
    损害
    0.38
    JACK
    0.37
    ARO
    0.37
    部长
    0.37
    राजा
    0.37
     //</
    0.37
    صفر
    0.37
    𝙠
    0.36
    Activations Density 0.003%

    No Known Activations