© 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. 42663
    Prev
    Next
    INDEX
    Explanations

    heavy hand, blow, duty, ion

    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
    j
    0.95
    n
    0.87
    o
    0.86
    I
    0.83
    ↵
    0.82
    í
    0.78
    the
    0.78
    ant
    0.75
    ิน
    0.75
    It
    0.74
    POSITIVE LOGITS
     لأ
    0.72
     Tatsache
    0.68
    р
    0.67
    рни
    0.64
    蘄
    0.64
    цей
    0.64
     основ
    0.63
    фта
    0.63
    เรา
    0.63
     particolari
    0.63
    Activations Density 0.003%

    No Known Activations