© 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. 90538
    Prev
    Next
    INDEX
    Explanations

    conference room

    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
    el
    0.76
     of
    0.74
    ن
    0.71
     Jews
    0.68
    ен
    0.67
    ات
    0.66
    न
    0.66
    ন
    0.65
    نی
    0.64
     coaster
    0.64
    POSITIVE LOGITS
    ແມ
    0.66
    bmod
    0.66
    深刻
    0.63
    प्रकाश
    0.61
    '
    0.61
    偏差
    0.60
    谐
    0.60
    ροφο
    0.59
    ແມ່ນ
    0.58
     карти
    0.58
    Activations Density 0.000%

    No Known Activations