© 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. 142886
    Prev
    Next
    INDEX
    Explanations

    exit

    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
    әт
    0.37
    𝑯
    0.36
    माने
    0.35
    द्वीप
    0.35
     Eti
    0.35
     fisik
    0.34
    Standard
    0.33
     Handwritten
    0.33
     Standardization
    0.33
     হুগ
    0.33
    POSITIVE LOGITS
    AsUp
    0.33
    关
    0.32
    ERING
    0.32
    ertools
    0.32
     Gone
    0.32
    купа
    0.31
     unwa
    0.31
    ♧
    0.31
    ering
    0.31
    osa
    0.30
    Activations Density 0.000%

    No Known Activations