© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82519
    Prev
    Next
    INDEX
    Explanations

    fall or fallen and associated concepts

    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_0_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
    in
    1.79
    k
    1.73
    i
    1.69
    ↵↵
    1.61
    d
    1.47
    지
    1.42
    ק
    1.30
    ด์
    1.26
    ють
    1.20
    ك
    1.20
    POSITIVE LOGITS
    ва
    1.27
    ো
    1.24
    ۰
    1.16
     progressed
    1.12
    и
    1.08
     finales
    1.06
     sentenced
    1.04
    BUT
    1.04
     fastened
    1.03
     moored
    1.02
    Activations Density 0.001%

    No Known Activations