© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195045
    Prev
    Next
    INDEX
    Explanations

    Plath FG AB ff FP IG f up hor av

    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_4_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
    ar
    0.49
    ان
    0.48
    ри
    0.45
    р
    0.44
    on
    0.43
    ol
    0.42
     weer
    0.41
    ва
    0.40
    ра
    0.39
    就需要
    0.38
    POSITIVE LOGITS
    s
    0.78
    d
    0.70
    y
    0.66
    m
    0.52
    '
    0.49
    नि
    0.48
    p
    0.48
    lių
    0.48
    t
    0.47
    li
    0.47
    Activations Density 0.002%

    No Known Activations