© 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. 44334
    Prev
    Next
    INDEX
    Explanations

    potluck

    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
    ↵
    0.75
    在
    0.68
    了很多
    0.66
    (
    0.65
    好
    0.61
     (
    0.59
    在那里
    0.59
     טוב
    0.57
     “
    0.57
    ER
    0.57
    POSITIVE LOGITS
    ۹
    1.02
    ،
    0.82
    ፣
    0.74
    ྪ
    0.73
    行う
    0.72
    ﺔ
    0.71
    ৭
    0.70
     कांस्टेबल
    0.69
    Emails
    0.69
    。\
    0.69
    Activations Density 0.000%

    No Known Activations