© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 198042
    Prev
    Next
    INDEX
    Explanations

    Popup visible, search results

    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_15_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
    د
    0.54
    S
    0.52
    У
    0.51
    ↵
    0.46
     velocities
    0.46
    Ре
    0.45
    ر
    0.44
     velocity
    0.43
    [,
    0.43
    ز
    0.42
    POSITIVE LOGITS
     remastered
    0.46
     confidentialité
    0.46
     கே
    0.45
     국민
    0.44
    due
    0.43
    签证
    0.43
    acamole
    0.43
    aya
    0.43
    iday
    0.43
    hooting
    0.43
    Activations Density 0.000%

    No Known Activations