© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38528
    Prev
    Next
    INDEX
    Explanations

    already talking about

    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_11_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
     ל
    0.64
     מ
    0.59
    ו
    0.55
    י
    0.52
    ש
    0.50
    ר
    0.50
    ת
    0.49
    ע
    0.49
    ری
    0.49
     bulund
    0.48
    POSITIVE LOGITS
    (
    0.43
    Few
    0.37
    S
    0.36
    IT
    0.36
    Side
    0.36
    ulate
    0.34
    \(
    0.34
    ectors
    0.34
    SIDE
    0.34
    P
    0.33
    Activations Density 0.010%

    No Known Activations