© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166831
    Prev
    Next
    INDEX
    Explanations

    disclaimers for content

    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_31_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
    納
    0.40
    くる
    0.38
     উচিৎ
    0.37
    媺
    0.37
    るのは
    0.37
     вя
    0.36
    軫
    0.35
    ান
    0.35
    voicing
    0.35
     ప్రభావ
    0.35
    POSITIVE LOGITS
     ਨਹੀਂ
    0.40
     honest
    0.37
     Goog
    0.36
     mountaine
    0.36
     pero
    0.36
     नहीं
    0.34
    crystalline
    0.33
     Kult
    0.33
     smoothies
    0.33
    ificacion
    0.33
    Activations Density 0.003%

    No Known Activations