© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79644
    Prev
    Next
    INDEX
    Explanations

    级 / level

    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
    ↵
    1.66
    ות
    1.59
    на
    1.57
    ים
    1.49
    いた
    1.43
    t
    1.43
    2
    1.43
     has
    1.38
     {
    1.35
     it
    1.31
    POSITIVE LOGITS
    н
    1.55
     I
    1.51
    ور
    1.29
    도
    1.20
     в
    1.16
     выпол
    1.16
    も
    1.16
    嶇
    1.16
    ン
    1.15
    ного
    1.14
    Activations Density 0.001%

    No Known Activations