© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21237
    Prev
    Next
    INDEX
    Explanations

    "-ed" descriptors

    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_56_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
    orsum
    0.38
    unless
    0.38
     Krebs
    0.36
    aji
    0.35
    ajno
    0.35
    线上
    0.34
     zert
    0.34
     Ð
    0.34
    اج
    0.33
     каттоо
    0.33
    POSITIVE LOGITS
     headed
    1.84
     handed
    1.84
     minded
    1.77
     sided
    1.73
     eyed
    1.73
    headed
    1.67
    handed
    1.59
    sided
    1.52
     faced
    1.50
    minded
    1.49
    Activations Density 0.063%

    No Known Activations