© 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. 127540
    Prev
    Next
    INDEX
    Explanations

    NCR, Sultanate

    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
    l
    0.75
    ل
    0.71
    c
    0.67
    Му
    0.63
    t
    0.61
     I
    0.60
    k
    0.59
    瓒
    0.59
    م
    0.59
    Error
    0.57
    POSITIVE LOGITS
     đạp
    0.66
     delighted
    0.64
     дели
    0.64
     ہے۔
    0.64
     виде
    0.64
     рейти
    0.64
     múlt
    0.63
     deletes
    0.63
    اوی
    0.62
    。
    0.62
    Activations Density 0.000%

    No Known Activations