© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 212888
    Prev
    Next
    INDEX
    Explanations

    crankshaft

    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_50_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
    Rusty
    0.43
     Rusty
    0.42
     Crash
    0.40
    >^
    0.39
     Ter
    0.38
     ter
    0.38
     autorización
    0.37
    ڑھ
    0.37
     Lever
    0.37
     Chauhan
    0.37
    POSITIVE LOGITS
    曲
    0.65
    곡
    0.58
     곡
    0.58
     曲
    0.53
     ve
    0.53
     K
    0.51
     curvatures
    0.49
     ক
    0.47
     cur
    0.44
     ک
    0.44
    Activations Density 0.000%

    No Known Activations