© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 119862
    Prev
    Next
    INDEX
    Explanations

    proxy configuration

    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_27_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
     durs
    0.46
     czł
    0.38
     Equest
    0.37
    MRT
    0.36
     malleable
    0.36
    督
    0.36
     PWR
    0.36
    SQLite
    0.35
    ầ
    0.35
     Poirot
    0.35
    POSITIVE LOGITS
     mapped
    0.42
    వు
    0.40
    mapped
    0.39
    映射
    0.38
     mapping
    0.38
     सुविधाएं
    0.38
    ૂ
    0.37
     ಉಪ
    0.36
     initiatives
    0.36
    ভিত্তিক
    0.36
    Activations Density 0.001%

    No Known Activations