© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39357
    Prev
    Next
    INDEX
    Explanations

    source

    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_3_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
    в
    0.84
    ات
    0.74
    та
    0.73
    ת
    0.70
    ის
    0.67
    ок
    0.67
     captivated
    0.66
    ี
    0.66
     obstruct
    0.64
    ः
    0.64
    POSITIVE LOGITS
    com
    0.69
    ino
    0.69
    源
    0.68
     in
    0.67
     source
    0.64
    ico
    0.63
    iet
    0.63
    Source
    0.63
    ew
    0.63
    vieve
    0.63
    Activations Density 0.005%

    No Known Activations