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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 53-GEMMASCOPE-2-TRANSCODER-262K
    4. 80216
    Prev
    Next
    INDEX
    Explanations

    scoring

    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_53_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
     H
    0.40
     Lenin
    0.38
     embarrass
    0.37
     embarrassed
    0.37
     Azte
    0.36
     Hose
    0.36
     embar
    0.36
    య్య
    0.33
    愛的
    0.33
    Gross
    0.33
    POSITIVE LOGITS
     Recreation
    0.44
     recreation
    0.41
     recre
    0.40
     Sprite
    0.40
     ખ
    0.39
     計
    0.38
     morphologies
    0.38
     Cuenta
    0.38
     vaporization
    0.38
    richter
    0.38
    Activations Density 0.000%

    No Known Activations