© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258512
    Prev
    Next
    INDEX
    Explanations

    iterations

    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_22_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    luor
    0.39
     preferring
    0.39
    ِل
    0.38
     আলোক
    0.38
    ⎛
    0.38
    عادة
    0.38
     ಅನುಪ
    0.38
     المهم
    0.38
     ഓഫ്
    0.38
     لمح
    0.37
    POSITIVE LOGITS
    antiene
    0.44
    Messi
    0.44
    ст
    0.42
    pessoa
    0.42
     friction
    0.42
    ாண
    0.42
     tendencias
    0.40
    atik
    0.40
    $',
    0.40
    સ્ત
    0.39
    Activations Density 0.000%

    No Known Activations