© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 222735
    Prev
    Next
    INDEX
    Explanations

    significant hurdle

    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_10_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
    Ко
    0.85
    Ро
    0.85
    Ни
    0.79
    До
    0.77
    Во
    0.76
    ي
    0.75
    К
    0.75
    Ка
    0.74
    Пре
    0.73
    И
    0.73
    POSITIVE LOGITS
    ta
    0.59
    ra
    0.59
     as
    0.57
    ting
    0.57
     st
    0.56
    as
    0.56
    ali
    0.56
     brass
    0.55
     p
    0.54
     gr
    0.54
    Activations Density 0.002%

    No Known Activations