© 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. 37776
    Prev
    Next
    INDEX
    Explanations

    red and blue balls or lights

    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
    ل
    0.85
    л
    0.80
     l
    0.77
    D
    0.73
    لیس
    0.71
    9
    0.68
    ר
    0.67
     k
    0.67
    .)
    0.66
    する
    0.66
    POSITIVE LOGITS
    \
    1.20
    '
    0.97
    ни
    0.82
    -
    0.82
    {
    0.80
    ные
    0.79
    (
    0.79
    :
    0.74
    _
    0.74
    ’
    0.71
    Activations Density 0.004%

    No Known Activations