© 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. 126078
    Prev
    Next
    INDEX
    Explanations

    melanie, melange, maker, chisholm

    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
     médian
    0.75
    นั้น
    0.73
    ्स
    0.71
    什么
    0.70
    ма
    0.68
    ｀)
    0.67
    عيد
    0.64
    şık
    0.63
    지와
    0.63
    tellers
    0.63
    POSITIVE LOGITS
    ana
    0.65
    iz
    0.64
    li
    0.63
     on
    0.63
    le
    0.58
     आठ
    0.58
    з
    0.58
    ry
    0.57
    ah
    0.57
    la
    0.57
    Activations Density 0.000%

    No Known Activations