© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 150796
    Prev
    Next
    INDEX
    Explanations

    past tense negative or restrictive verbs

    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_23_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
     является
    0.32
     являются
    0.31
    aspectj
    0.31
    iali
    0.31
     peor
    0.31
     러시아
    0.30
     गैंग
    0.30
    ^{*}$
    0.30
     μία
    0.29
     брон
    0.29
    POSITIVE LOGITS
    カーボン
    0.30
    벗
    0.30
    棹
    0.30
    تج
    0.30
    䒠
    0.30
    罄
    0.29
     totales
    0.29
    槁
    0.29
    日まで
    0.29
     comps
    0.29
    Activations Density 0.041%

    No Known Activations