© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44111
    Prev
    Next
    INDEX
    Explanations

    words after "un" or "actually"

    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_13_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
    ata
    0.58
     பத்து
    0.50
    iche
    0.50
    ayan
    0.49
    trump
    0.48
    interno
    0.48
    unday
    0.47
     ﺍ
    0.47
    oto
    0.47
    nich
    0.47
    POSITIVE LOGITS
    坊
    0.47
     kurzer
    0.46
    ః
    0.46
     vannak
    0.46
     morrer
    0.45
    慢
    0.44
     exercised
    0.44
     mingle
    0.44
    ловой
    0.44
     cuer
    0.43
    Activations Density 0.000%

    No Known Activations