© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48497
    Prev
    Next
    INDEX
    Explanations

    today's date

    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_31_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
    단을
    0.38
    лды
    0.33
    riso
    0.33
    هایت
    0.33
     শিল্প
    0.33
    "-
    0.32
    ρών
    0.32
     restoring
    0.32
     salió
    0.32
    <0x9B>
    0.32
    POSITIVE LOGITS
    PPT
    0.37
     PPT
    0.36
     conceived
    0.35
    ێت
    0.35
     понятия
    0.35
    ColorF
    0.34
     सूरत
    0.34
    াপি
    0.33
    ጹ
    0.33
     IPT
    0.33
    Activations Density 0.002%

    No Known Activations