© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 196476
    Prev
    Next
    INDEX
    Explanations

    bal

    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_50_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
     pint
    0.57
     Pint
    0.48
     ピ
    0.41
     pys
    0.40
    picode
    0.40
    sberg
    0.39
    pint
    0.39
     pints
    0.38
    ớp
    0.38
    ピ
    0.38
    POSITIVE LOGITS
     bal
    1.56
     Bal
    1.51
    Bal
    1.48
    bal
    1.31
     BAL
    1.29
    BAL
    1.28
     бал
    1.13
     بال
    1.02
     Бал
    0.97
     Бала
    0.94
    Activations Density 0.000%

    No Known Activations