© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 61953
    Prev
    Next
    INDEX
    Explanations

    dtype, dtypes, ctypes

    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_2_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
    n
    2.31
    r
    2.14
    l
    1.77
    m
    1.73
    ר
    1.71
    is
    1.56
    the
    1.55
    for
    1.47
    т
    1.31
    il
    1.28
    POSITIVE LOGITS
    ك
    1.34
    ح
    1.33
    เรา
    1.27
     amelyet
    1.16
     joka
    1.13
     ganze
    1.13
    kter
    1.13
    無い
    1.12
    ков
    1.11
    ku
    1.08
    Activations Density 0.004%

    No Known Activations