© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14172
    Prev
    Next
    INDEX
    Explanations

    abstract class methods

    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_13_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
    y
    0.55
    ９
    0.48
     inglés
    0.46
    நீங்கள்
    0.46
     отсутствии
    0.46
     gdy
    0.45
    %");
    0.45
     ड
    0.45
     uygul
    0.45
     gobierno
    0.45
    POSITIVE LOGITS
     other
    0.44
    Gli
    0.42
    ining
    0.42
    isodes
    0.42
     functionalities
    0.41
    endosi
    0.41
    istem
    0.41
    èdent
    0.40
    ied
    0.40
    ilibrium
    0.40
    Activations Density 0.012%

    No Known Activations