© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 217583
    Prev
    Next
    INDEX
    Explanations

    refer to, among youth, far cry, hardships she

    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_16_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
     выпол
    0.48
    exécution
    0.47
    ிருஷ்
    0.45
    Muhammad
    0.45
    💞
    0.45
    nltk
    0.45
    ︿
    0.43
    学校
    0.43
    했습니다
    0.43
     सुविधाजनक
    0.42
    POSITIVE LOGITS
     and
    0.61
     dominance
    0.52
     complains
    0.51
     및
    0.50
     instability
    0.49
     plead
    0.48
     dominates
    0.47
     plugs
    0.47
     stimulates
    0.47
     inadvertently
    0.46
    Activations Density 0.000%

    No Known Activations