© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 121498
    Prev
    Next
    INDEX
    Explanations

    monthly active users

    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_38_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
    离开
    0.53
    驶
    0.45
    离开了
    0.45
    離開
    0.43
    仆
    0.42
     நிலையம்
    0.42
    逃
    0.40
     depart
    0.40
     departs
    0.40
    ovit
    0.39
    POSITIVE LOGITS
    Bak
    0.45
    npcs
    0.43
    bak
    0.41
     Bak
    0.38
     bak
    0.38
     extrad
    0.37
    $%
    0.37
    Main
    0.36
     imam
    0.35
    殉
    0.35
    Activations Density 0.000%

    No Known Activations