© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 64583
    Prev
    Next
    INDEX
    Explanations

    después

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    getLast
    0.46
    针
    0.42
    ulları
    0.40
     doth
    0.39
     సన్నివేశ
    0.39
     ይመ
    0.39
     потім
    0.39
     fulfils
    0.39
    न्दे
    0.39
    তারপর
    0.39
    POSITIVE LOGITS
    拐
    0.37
     housed
    0.36
    dur
    0.35
    izacion
    0.35
     Dewey
    0.35
     પાસેથી
    0.35
     opposite
    0.34
    AboutDlg
    0.34
    Tic
    0.33
    SELECT
    0.33
    Activations Density 0.002%

    No Known Activations