© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45413
    Prev
    Next
    INDEX
    Explanations

    bed frame Bath Springs

    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
     for
    0.75
    f
    0.66
    ानंतर
    0.65
    ěji
    0.63
    انس
    0.62
    h
    0.61
    for
    0.59
    voud
    0.57
    fst
    0.56
    pw
    0.55
    POSITIVE LOGITS
    सर्गिक
    0.70
    روی
    0.66
     intégr
    0.65
     ดี
    0.64
     nâng
    0.63
    swell
    0.62
    ла
    0.61
    :
    0.61
     এয়ার
    0.61
    rental
    0.61
    Activations Density 0.000%

    No Known Activations