© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77570
    Prev
    Next
    INDEX
    Explanations

    balance chemical equations

    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_31_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
    적
    0.33
    osph
    0.28
     constellation
    0.27
    リーズ
    0.27
    Ин
    0.25
    畯
    0.25
    Drop
    0.25
     оформ
    0.25
     pg
    0.25
     эм
    0.25
    POSITIVE LOGITS
     subtracted
    0.28
    මු
    0.28
     продаже
    0.27
    पुरम
    0.26
     Dessous
    0.25
     Presently
    0.25
    즙
    0.25
    परीक्षा
    0.24
     dijual
    0.24
    ებში
    0.24
    Activations Density 0.003%

    No Known Activations