© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111319
    Prev
    Next
    INDEX
    Explanations

    of a bend

    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_2_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
    I
    0.79
    س
    0.73
    น
    0.66
    ش
    0.61
    ن
    0.60
    ม
    0.57
    ส
    0.57
    R
    0.56
    acks
    0.55
    ike
    0.53
    POSITIVE LOGITS
    t
    1.13
    tól
    0.68
    tR
    0.64
    r
    0.61
    ৫
    0.61
    ции
    0.58
    tı
    0.56
    lük
    0.56
    tive
    0.56
    tà
    0.54
    Activations Density 0.000%

    No Known Activations