© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 88566
    Prev
    Next
    INDEX
    Explanations

    pdf, pdp, password, conditioned

    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
     \
    0.69
    اری
    0.63
    ai
    0.61
     словам
    0.61
    ส
    0.61
    0.60
    ิ
    0.59
    ו
    0.59
    LOR
    0.58
    อน
    0.57
    POSITIVE LOGITS
    ال
    0.80
    ת
    0.70
    gård
    0.70
    gatt
    0.67
    т
    0.67
    kow
    0.66
    上
    0.66
    that
    0.65
    រយៈពេល
    0.65
    kon
    0.64
    Activations Density 0.000%

    No Known Activations