© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144425
    Prev
    Next
    INDEX
    Explanations

    danced with prepositions

    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_0_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
    widgetTo
    1.22
    くらい
    1.20
     فونبټ
    1.19
    。
    1.16
    지
    1.15
    나
    1.15
     кораб
    1.12
    fdPar
    1.11
    squre
    1.09
     بالټ
    1.09
    POSITIVE LOGITS
    h
    2.55
    y
    2.34
    ia
    2.19
    o
    2.08
    c
    2.02
    w
    1.98
    ing
    1.96
    un
    1.93
    e
    1.93
    p
    1.84
    Activations Density 0.000%

    No Known Activations