© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130056
    Prev
    Next
    INDEX
    Explanations

    red

    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_6_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
    '
    1.54
    น
    1.07
    л
    0.95
    ו
    0.89
    та
    0.88
    {
    0.88
    ל
    0.88
     wre
    0.87
    (
    0.86
    "
    0.84
    POSITIVE LOGITS
    ত্যাশিত
    0.76
     පිළිබඳ
    0.75
     ತುಂಬಾ
    0.73
    ā
    0.73
     கடுமையான
    0.71
     spraying
    0.71
     bestowed
    0.71
    します
    0.71
     സംസാ
    0.70
     በጣም
    0.70
    Activations Density 0.006%

    No Known Activations