© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88763
    Prev
    Next
    INDEX
    Explanations

    Italian, Australian, or related to words ending in ism

    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_3_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
    s
    0.85
    m
    0.83
    Second
    0.83
    et
    0.81
    á
    0.80
    nd
    0.77
     Second
    0.77
    tin
    0.76
    tı
    0.76
     দ্বিতীয়
    0.73
    POSITIVE LOGITS
    ר
    0.64
     પાસે
    0.63
     sya
    0.63
     Mara
    0.61
    सिले
    0.60
    )]^{
    0.59
     oso
    0.59
     лише
    0.59
     evas
    0.59
     sulle
    0.58
    Activations Density 0.000%

    No Known Activations