© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230546
    Prev
    Next
    INDEX
    Explanations

    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_6_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
    ’
    1.47
    u
    1.22
    a
    1.01
    on
    1.00
    et
    0.96
    o
    0.95
    7
    0.95
    2
    0.95
    就
    0.95
    3
    0.91
    POSITIVE LOGITS
     αλλά
    0.94
     carbonates
    0.93
     punctures
    0.90
    phed
    0.89
     فی
    0.88
     copyspace
    0.86
     dentées
    0.85
    ாவின்
    0.84
     ถึง
    0.84
    𒌆
    0.84
    Activations Density 0.000%

    No Known Activations