© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33137
    Prev
    Next
    INDEX
    Explanations

    you judge

    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_40_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
     judgement
    0.46
    莞
    0.44
     judgment
    0.44
     Judgment
    0.42
     judgmental
    0.41
     Auswahl
    0.41
    Regulatory
    0.41
    regulatory
    0.40
    助
    0.40
    judgment
    0.39
    POSITIVE LOGITS
     presided
    0.47
     presiding
    0.46
     Joan
    0.40
     bananas
    0.40
    Joan
    0.39
     be
    0.39
     Be
    0.38
     sole
    0.38
     deliberations
    0.37
    korn
    0.37
    Activations Density 0.058%

    No Known Activations