© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27689
    Prev
    Next
    INDEX
    Explanations

    Times Square

    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_10_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
    niers
    0.56
    ни
    0.55
    Directories
    0.54
    ι
    0.54
    lardan
    0.53
    Wid
    0.53
    itements
    0.53
    й
    0.52
    psies
    0.51
    ુ
    0.50
    POSITIVE LOGITS
     of
    0.68
     with
    0.60
     Frag
    0.59
     as
    0.57
     Candy
    0.57
     into
    0.56
     only
    0.55
     canned
    0.54
     Astro
    0.54
     Mille
    0.54
    Activations Density 0.000%

    No Known Activations