© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78912
    Prev
    Next
    INDEX
    Explanations

    appearances and displays

    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_0_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
    er
    1.59
    :
    1.59
    i
    1.58
    ck
    1.34
    manship
    1.29
    ali
    1.28
    ii
    1.25
     (
    1.24
    icals
    1.23
    ien
    1.23
    POSITIVE LOGITS
    ן
    2.08
    é
    1.95
    ی
    1.84
    ની
    1.76
    는
    1.67
    は
    1.66
    ע
    1.63
    起こ
    1.57
    に
    1.56
    ા
    1.55
    Activations Density 0.002%

    No Known Activations