© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14793
    Prev
    Next
    INDEX
    Explanations

    encryption at rest

    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_15_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
     subtypes
    0.42
     deficiency
    0.42
    arked
    0.41
     fij
    0.39
     neoplasms
    0.39
    𝘁
    0.39
     perpetrator
    0.39
    კის
    0.39
     etiology
    0.39
    龍
    0.39
    POSITIVE LOGITS
    คุณ
    0.47
    Mexico
    0.46
    Bạn
    0.46
     bạn
    0.46
    an
    0.46
    Australia
    0.44
    Friends
    0.43
    വിടെ
    0.43
    A
    0.43
    አ
    0.43
    Activations Density 0.001%

    No Known Activations