© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20077
    Prev
    Next
    INDEX
    Explanations

    judgment flows

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     सप
    0.39
     Lut
    0.38
     bare
    0.34
     specialize
    0.34
     createCanvas
    0.34
     কণ
    0.34
    粉
    0.34
    果た
    0.34
    အစား
    0.33
     האי
    0.33
    POSITIVE LOGITS
     judgment
    1.65
     flows
    1.57
     judgement
    1.49
     Judgment
    1.48
    judgment
    1.45
    Judgment
    1.45
     Flows
    1.23
     jugement
    1.15
     judg
    1.14
    判断
    1.08
    Activations Density 0.011%

    No Known Activations