© 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. 80973
    Prev
    Next
    INDEX
    Explanations

    securing the things

    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
    have
    1.40
    یی
    1.37
    に
    1.16
    chaoxing
    1.11
    u
    1.09
    いる
    1.04
    kannya
    1.03
    phones
    1.02
    tong
    1.00
    t
    0.98
    POSITIVE LOGITS
    л
    1.85
    ס
    1.85
    ק
    1.77
    น
    1.62
    ة
    1.59
     in
    1.58
    ד
    1.56
    ল
    1.50
    н
    1.49
    ন
    1.49
    Activations Density 0.001%

    No Known Activations