© 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. 217740
    Prev
    Next
    INDEX
    Explanations

    future forecasting

    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
     hedging
    0.59
     nanop
    0.54
     싶
    0.52
     hedge
    0.50
    ร้อม
    0.50
    тріш
    0.49
    ISAM
    0.49
     heparin
    0.49
     venom
    0.49
     사용할
    0.48
    POSITIVE LOGITS
    n
    0.57
    v
    0.54
    Global
    0.51
    famous
    0.49
     muchas
    0.48
    b
    0.48
    By
    0.47
    |
    0.47
    cong
    0.46
    cul
    0.46
    Activations Density 0.000%

    No Known Activations