© 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. 44803
    Prev
    Next
    INDEX
    Explanations

    Y2Mate, Sense, offset

    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
    是
    0.78
    an
    0.73
    는
    0.65
    2
    0.63
    は
    0.62
    ان
    0.62
    1
    0.60
    al
    0.60
    r
    0.59
    n
    0.57
    POSITIVE LOGITS
    ৮
    0.76
     not
    0.71
     finir
    0.66
    ет
    0.63
    ਪ
    0.63
    ৯
    0.63
    ्रेडिट
    0.62
    ای
    0.61
    NING
    0.61
    𝘷
    0.61
    Activations Density 0.000%

    No Known Activations