© 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. 207671
    Prev
    Next
    INDEX
    Explanations

    styled components

    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
    रीत
    0.43
    iPad
    0.40
     Vert
    0.40
     程
    0.39
     Lourdes
    0.39
     chewed
    0.39
    रिट
    0.38
    _^
    0.38
    畤
    0.38
     Haz
    0.37
    POSITIVE LOGITS
     outfile
    0.37
     momentum
    0.36
    uti
    0.35
    Nullable
    0.35
     inm
    0.35
     pdelay
    0.35
     turbulence
    0.35
    able
    0.34
    Gen
    0.33
    provider
    0.33
    Activations Density 0.000%

    No Known Activations