© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97564
    Prev
    Next
    INDEX
    Explanations

    odds and ratio

    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_14_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
     H
    0.52
    ﺝ
    0.49
    MASTER
    0.49
    影片
    0.49
    ចាប់
    0.48
    ದ್ದ
    0.48
    CHAPTER
    0.47
    USU
    0.46
    INGS
    0.45
    Logs
    0.45
    POSITIVE LOGITS
    ъ
    0.52
    迅速
    0.52
    Enumerator
    0.51
    вов
    0.49
    undle
    0.49
    മതി
    0.47
    ’;
    0.46
     spokesperson
    0.46
    бл
    0.46
    تالي
    0.46
    Activations Density 0.000%

    No Known Activations