© 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. 195240
    Prev
    Next
    INDEX
    Explanations

    Find

    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
     R
    0.40
     grano
    0.39
     greenish
    0.38
     Password
    0.38
     passen
    0.38
     զ
    0.38
    ል
    0.37
     addr
    0.36
     outboard
    0.35
     தெரியும்
    0.35
    POSITIVE LOGITS
    狐
    0.43
    )/\
    0.40
    INAL
    0.39
    㠻
    0.39
    VEST
    0.39
    𝜋
    0.38
     Mixtures
    0.38
    㭋
    0.38
     پە
    0.37
    Références
    0.37
    Activations Density 0.001%

    No Known Activations