© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107485
    Prev
    Next
    INDEX
    Explanations

    Tsinghua University KEG

    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_1_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
    t
    2.23
    0
    1.90
    f
    1.85
    v
    1.80
    r
    1.79
    1
    1.69
    y
    1.64
    b
    1.60
    u
    1.59
    im
    1.58
    POSITIVE LOGITS
    ва
    1.13
    м
    1.02
    ер
    1.01
    setRoi
    0.91
     불구하고
    0.90
     едно
    0.89
    にする
    0.87
     energije
    0.85
     договор
    0.83
     характер
    0.83
    Activations Density 0.001%

    No Known Activations