© 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. 125668
    Prev
    Next
    INDEX
    Explanations

    Jack Black, Chagall, jack stands

    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
    m
    0.88
     harapan
    0.73
    ował
    0.69
    ın
    0.69
    ı
    0.66
    iaus
    0.66
    he
    0.65
     janvier
    0.65
     buộc
    0.65
    考え
    0.64
    POSITIVE LOGITS
    t
    0.70
    р
    0.68
    reactant
    0.64
    бно
    0.63
    ر
    0.63
    tax
    0.62
    captcha
    0.62
    ин
    0.61
     Пет
    0.61
    gz
    0.61
    Activations Density 0.000%

    No Known Activations