© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    4. 62361
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_41_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
     Schmitt
    0.39
     Bello
    0.38
    anilide
    0.38
     :+:
    0.37
     Amplify
    0.36
     शेअर
    0.36
    পা
    0.36
     interesados
    0.36
     부탁
    0.36
    ):["
    0.36
    POSITIVE LOGITS
     face
    0.43
    伍
    0.39
     ect
    0.38
    face
    0.38
    jing
    0.35
     Face
    0.35
     GW
    0.35
     court
    0.34
    gew
    0.34
    ేక
    0.34
    Activations Density 0.000%

    No Known Activations