© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27060
    Prev
    Next
    INDEX
    Explanations

    android.app.Service

    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_40_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
     m
    0.46
    根
    0.45
     fs
    0.44
     widest
    0.43
     м
    0.40
     mobile
    0.40
     unchanged
    0.39
     móvil
    0.39
     Maven
    0.39
    mani
    0.39
    POSITIVE LOGITS
     服务
    0.42
     서비스
    0.40
     خدمة
    0.40
    服務
    0.39
    協助
    0.39
    bboxes
    0.39
    ള്
    0.38
    뻑
    0.38
    ंदे
    0.38
     सर्विस
    0.38
    Activations Density 0.000%

    No Known Activations