© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57722
    Prev
    Next
    INDEX
    Explanations

    adjusting or 调整

    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_11_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
     D
    0.77
     d
    0.75
     °
    0.72
     H
    0.66
     o
    0.65
     c
    0.64
     k
    0.63
     DIY
    0.61
     section
    0.60
     sb
    0.60
    POSITIVE LOGITS
    t
    0.71
    Decre
    0.57
    Quiet
    0.55
    ोस
    0.55
    <0xED>
    0.54
    MINOR
    0.54
    וה
    0.54
    ف
    0.54
    Defer
    0.53
    ton
    0.53
    Activations Density 0.001%

    No Known Activations