© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132270
    Prev
    Next
    INDEX
    Explanations

    land designations

    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_6_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
    iamo
    1.09
     thiab
    1.06
     I
    1.01
     जिसके
    0.99
     Vielen
    0.99
    {
    0.96
    ၊
    0.89
     hvilket
    0.86
     sareng
    0.84
     घुल
    0.84
    POSITIVE LOGITS
    ن
    1.57
    an
    1.52
    ל
    1.46
    as
    1.41
    न
    1.39
    ন
    1.38
    ل
    1.34
    ب
    1.31
    ב
    1.26
    in
    1.22
    Activations Density 0.001%

    No Known Activations