© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38857
    Prev
    Next
    INDEX
    Explanations

    extremely + adjective/adverb

    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_11_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
    )。
    0.50
    ו
    0.50
    かる
    0.46
    apä
    0.45
    Buenas
    0.45
     συγκεκρι
    0.43
    》。
    0.42
     veía
    0.42
    姮
    0.41
    的研究
    0.41
    POSITIVE LOGITS
    into
    0.57
    pairwise
    0.53
     by
    0.52
    тому
    0.52
    ner
    0.50
     Using
    0.50
    through
    0.50
    ther
    0.49
    том
    0.49
    dua
    0.49
    Activations Density 0.011%

    No Known Activations