© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 44302
    Prev
    Next
    INDEX
    Explanations

    diverging, diffusers, diffusion

    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
    は
    0.68
    え
    0.68
    ห
    0.65
    ді
    0.65
    하다
    0.63
    а
    0.63
    লিশ
    0.62
    로
    0.61
    सना
    0.59
     a
    0.57
    POSITIVE LOGITS
    m
    1.07
    ó
    0.93
    y
    0.87
    b
    0.86
    k
    0.82
    i
    0.82
    IG
    0.80
     diverging
    0.77
     GSi
    0.76
    r
    0.74
    Activations Density 0.021%

    No Known Activations