© 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. 18742
    Prev
    Next
    INDEX
    Explanations

    second order or fourth order

    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
    ায়ন
    0.38
    ອາ
    0.38
     tunnelling
    0.38
     leaking
    0.36
     러시아
    0.36
     leakage
    0.36
    𠃊
    0.35
    शिक
    0.35
    ुए
    0.35
     radiation
    0.34
    POSITIVE LOGITS
     גבוה
    0.41
    穆
    0.39
    ENO
    0.39
     Systematic
    0.38
     Fourth
    0.38
    Fourth
    0.38
    compact
    0.37
     उच्च
    0.37
     Second
    0.37
     Compact
    0.36
    Activations Density 0.053%

    No Known Activations