© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46486
    Prev
    Next
    INDEX
    Explanations

    financial operations and impacts

    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_13_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
    жна
    0.54
    ﺪ
    0.52
    ౪
    0.50
    지도
    0.49
    ɖ
    0.48
     твор
    0.48
     доме
    0.48
    𝔬
    0.48
    ਅ
    0.47
     coating
    0.47
    POSITIVE LOGITS
    Lam
    0.50
    whale
    0.50
    Más
    0.49
     ;
    0.48
     Abyss
    0.48
    Members
    0.46
    Liability
    0.46
    Limit
    0.46
    Bolt
    0.46
    Flush
    0.46
    Activations Density 0.018%

    No Known Activations