© 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. 125380
    Prev
    Next
    INDEX
    Explanations

    applications and frameworks

    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
    ل
    1.13
    et
    1.08
    ang
    1.00
    am
    0.98
    er
    0.89
    is
    0.89
    en
    0.86
    ing
    0.82
    م
    0.81
    ला
    0.81
    POSITIVE LOGITS
     функция
    0.70
    ၉
    0.67
     партия
    0.62
    ৬
    0.62
     এলাকার
    0.62
     ứng
    0.60
    явления
    0.60
    Игра
    0.60
     приложения
    0.60
    ?")
    0.60
    Activations Density 0.000%

    No Known Activations