© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158208
    Prev
    Next
    INDEX
    Explanations

    ejecución

    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_2_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
    م
    1.79
    ל
    1.55
    מ
    1.34
    ।
    1.25
    د
    1.20
    м
    1.19
     I
    1.17
    س
    1.17
    נ
    1.13
    ä
    1.12
    POSITIVE LOGITS
    is
    1.28
    AR
    1.07
    ad
    0.95
    IR
    0.93
    <0x80>
    0.92
    UN
    0.92
    UR
    0.91
    ITION
    0.87
    ᱐
    0.86
    an
    0.85
    Activations Density 0.000%

    No Known Activations