© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 207359
    Prev
    Next
    INDEX
    Explanations

    languages and scripts

    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_46_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
     Nun
    0.44
     nun
    0.40
    amental
    0.39
    数组
    0.39
    ぐる
    0.38
    ⊆
    0.38
     seules
    0.38
    ⚕
    0.38
     Liquid
    0.38
     nuns
    0.38
    POSITIVE LOGITS
    MAP
    0.40
    imdb
    0.38
    образие
    0.38
     ठर
    0.36
    rach
    0.34
    eringen
    0.34
     Joc
    0.34
    호를
    0.33
    Ճ
    0.33
     wheat
    0.33
    Activations Density 0.000%

    No Known Activations