© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52372
    Prev
    Next
    INDEX
    Explanations

    elliptic curve cryptography

    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_31_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
    龺
    0.41
     комнаты
    0.40
    ークル
    0.39
    ページの
    0.38
     eukaryotes
    0.37
    ().__
    0.36
     মশ
    0.36
    TrackedDevice
    0.35
    家具
    0.35
    զ
    0.35
    POSITIVE LOGITS
     Benedict
    0.40
     Rational
    0.39
     tattoo
    0.38
    irati
    0.36
    rational
    0.36
    opic
    0.35
     SMS
    0.35
     concede
    0.35
     swing
    0.35
     Caribbean
    0.35
    Activations Density 0.003%

    No Known Activations