© 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. 42441
    Prev
    Next
    INDEX
    Explanations

    rolling up

    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
    ходе
    0.70
    ام
    0.69
    ig
    0.66
    них
    0.64
    ца
    0.64
    ль
    0.63
    сах
    0.63
    ة
    0.62
    ية
    0.61
    ме
    0.61
    POSITIVE LOGITS
    ו
    0.68
    with
    0.65
    you
    0.64
    어요
    0.64
     don
    0.63
    “
    0.61
     anot
    0.60
     fenomen
    0.59
    out
    0.58
     pacif
    0.57
    Activations Density 0.007%

    No Known Activations