© 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. 18099
    Prev
    Next
    INDEX
    Explanations

    object detection

    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
    ключа
    0.36
    ၿ
    0.36
    рам
    0.35
    чна
    0.35
    CharAt
    0.34
    北美
    0.34
    촬
    0.33
    час
    0.33
    ូប
    0.33
    جهه
    0.33
    POSITIVE LOGITS
    ers
    0.50
     Código
    0.50
    ada
    0.46
    ées
    0.46
    ante
    0.45
    7
    0.45
    ido
    0.44
    3
    0.44
     artículos
    0.44
     código
    0.43
    Activations Density 0.000%

    No Known Activations