© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137130
    Prev
    Next
    INDEX
    Explanations

    special spaces and zero-width characters

    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_12_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
    inum
    0.38
    apha
    0.36
    प्ता
    0.35
    not
    0.35
    inus
    0.34
    ✿
    0.34
    dif
    0.34
    azione
    0.34
    islav
    0.33
    urno
    0.33
    POSITIVE LOGITS
     было
    0.38
     byla
    0.36
     R
    0.36
     RCLCPP
    0.36
     byly
    0.34
     были
    0.34
     leider
    0.34
     сути
    0.34
     была
    0.34
     кода
    0.33
    Activations Density 0.000%

    No Known Activations