© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 197392
    Prev
    Next
    INDEX
    Explanations

    extra data or values

    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_15_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
    z
    0.64
    <0x0D>
    0.61
    ste
    0.61
    er
    0.59
    ske
    0.59
    zo
    0.59
    h
    0.59
    i
    0.59
    n
    0.57
    inter
    0.57
    POSITIVE LOGITS
     Manit
    0.58
     اڈوں
    0.57
    امل
    0.56
     سانت
    0.54
    InputDir
    0.54
     antiga
    0.53
    ᠴ
    0.53
     Thủ
    0.52
     samarbe
    0.52
    Бар
    0.52
    Activations Density 0.000%

    No Known Activations