© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107811
    Prev
    Next
    INDEX
    Explanations

    text-sm

    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_1_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
    ని
    1.09
    \
    0.99
     불구하고
    0.86
    ल
    0.83
    ता
    0.79
     може
    0.75
     पड़ेगा
    0.75
     großer
    0.75
     хватает
    0.75
     قادر
    0.75
    POSITIVE LOGITS
    a
    1.73
    p
    1.52
     can
    1.48
    ン
    1.47
    ید
    1.32
    A
    1.29
    AV
    1.26
    ing
    1.16
    ac
    1.16
    MB
    1.16
    Activations Density 0.001%

    No Known Activations