© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 140211
    Prev
    Next
    INDEX
    Explanations

    iterating directory listing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_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
     excretion
    0.40
    screw
    0.39
    追い
    0.38
     rip
    0.38
    뜹
    0.38
     screw
    0.38
    ForgotPassword
    0.37
     dynamic
    0.37
    Vice
    0.37
    ],'
    0.36
    POSITIVE LOGITS
     Dat
    0.38
     ă
    0.36
     drake
    0.36
     su
    0.35
    ẹn
    0.35
    helloworld
    0.34
     Sa
    0.34
     παν
    0.33
    accharide
    0.33
    一身
    0.33
    Activations Density 0.050%

    No Known Activations