© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53348
    Prev
    Next
    INDEX
    Explanations

    equality operations

    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_30_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
     dist
    0.34
    の実
    0.33
     हराया
    0.31
    역
    0.31
     vær
    0.30
     edges
    0.30
     stole
    0.29
     역
    0.29
     недоста
    0.28
     stolen
    0.28
    POSITIVE LOGITS
     unchanged
    0.46
     egalitarian
    0.43
    Equals
    0.42
    Equality
    0.42
    ស្
    0.41
     iguales
    0.41
     같
    0.41
     Equality
    0.40
     gelijk
    0.40
    equality
    0.39
    Activations Density 0.072%

    No Known Activations