© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57686
    Prev
    Next
    INDEX
    Explanations

    preface this

    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_11_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
    an
    0.82
    ان
    0.61
    ా
    0.60
    as
    0.59
    at
    0.57
    ва
    0.55
    ون
    0.55
    a
    0.50
    انة
    0.49
     naps
    0.49
    POSITIVE LOGITS
     मिट्टी
    0.48
    rie
    0.46
    渗透
    0.46
     \
    0.46
     է
    0.46
    ką
    0.45
    dió
    0.45
    ){}^
    0.45
    rieg
    0.45
    $)
    0.45
    Activations Density 0.016%

    No Known Activations