© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81417
    Prev
    Next
    INDEX
    Explanations

    knitting

    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
    س
    2.06
    ی
    1.52
    tedir
    1.46
    та
    1.33
    ف
    1.31
    ו
    1.28
    $,
    1.24
    、
    1.24
    ،
    1.24
    to
    1.18
    POSITIVE LOGITS
    5
    1.63
    ed
    1.62
    i
    1.61
    .
    1.59
    em
    1.59
    ipe
    1.50
    4
    1.48
    n
    1.43
    ere
    1.39
    il
    1.38
    Activations Density 0.000%

    No Known Activations