© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82643
    Prev
    Next
    INDEX
    Explanations

    advertising pages

    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_0_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
    ת
    1.77
    ك
    1.70
    ко
    1.44
    י
    1.38
    ה
    1.34
    ే
    1.31
    ل
    1.30
    ル
    1.27
    。"
    1.27
    ید
    1.26
    POSITIVE LOGITS
    s
    2.23
    ς
    1.74
    (
    1.73
    {
    1.54
    ים
    1.53
     (
    1.45
     repercussions
    1.38
    та
    1.24
    ată
    1.20
     incandescent
    1.20
    Activations Density 0.001%

    No Known Activations