© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139099
    Prev
    Next
    INDEX
    Explanations

    max and min comparison

    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_12_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
    ;
    0.67
    f
    0.64
    n
    0.61
    t
    0.58
    ed
    0.57
    ки
    0.54
    k
    0.54
     assortment
    0.53
     cuddling
    0.53
    g
    0.53
    POSITIVE LOGITS
     जमिनी
    0.58
    呼び
    0.57
     جنگ
    0.55
     خواست
    0.55
    раль
    0.55
    льные
    0.54
    Autres
    0.54
     انگ
    0.53
    しない
    0.53
    者に
    0.53
    Activations Density 0.000%

    No Known Activations