© 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. 42755
    Prev
    Next
    INDEX
    Explanations

    evenly-matched east Asian women

    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
    ༤
    0.71
    ﻤ
    0.70
    g
    0.66
    ﻪ
    0.66
    塀
    0.66
    ﯼ
    0.65
    də
    0.64
    sensitivity
    0.64
    s
    0.64
    dear
    0.63
    POSITIVE LOGITS
     revital
    0.65
    ig
    0.64
     It
    0.59
     to
    0.58
     v
    0.58
    厷
    0.57
    </h3>
    0.57
    ít
    0.56
     Ress
    0.56
    该
    0.55
    Activations Density 0.002%

    No Known Activations