© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 195935
    Prev
    Next
    INDEX
    Explanations

    adverbs ending in -mente, -ly, -ment, -able, etc

    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_27_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
    育
    0.33
     imput
    0.33
     infine
    0.32
     maravilh
    0.32
     morphogenesis
    0.32
    分別
    0.31
     recyclerView
    0.31
     доступа
    0.30
     অন্যতম
    0.30
     nourrir
    0.30
    POSITIVE LOGITS
    hem
    0.36
    ilized
    0.33
    Č
    0.33
    ere
    0.33
    atin
    0.32
     Puente
    0.32
    vian
    0.31
    Ç
    0.31
    Ć
    0.31
    اة
    0.30
    Activations Density 0.004%

    No Known Activations