© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89677
    Prev
    Next
    INDEX
    Explanations

    transvaginal, mutation, transsexual

    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_3_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
    r
    0.93
    <0x80>
    0.89
    m
    0.80
    an
    0.80
    ly
    0.77
    ed
    0.76
    يء
    0.76
    s
    0.73
    ر
    0.73
    ни
    0.72
    POSITIVE LOGITS
     to
    0.75
    را
    0.71
    در
    0.66
    ۳
    0.66
    ภาพ
    0.66
    द
    0.65
    รา
    0.65
    to
    0.64
    आई
    0.64
    ری
    0.63
    Activations Density 0.001%

    No Known Activations