© 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
    2. Gemma-3-27B-IT
    3. 23-GEMMASCOPE-2-TRANSCODER-262K
    4. 87235
    Prev
    Next
    INDEX
    Explanations

    comma followed by pronoun

    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_23_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
     프
    0.44
     프리
    0.44
    퍼
    0.42
    ﹀
    0.41
    JAV
    0.40
    布
    0.39
    프
    0.39
     퍼
    0.39
     frågor
    0.39
     cryptocurrency
    0.39
    POSITIVE LOGITS
     ໜອງ
    0.48
    ari
    0.45
    ક્રિય
    0.45
    relating
    0.43
    asList
    0.43
    ion
    0.42
    criar
    0.41
     being
    0.40
    un
    0.40
    adri
    0.39
    Activations Density 0.001%

    No Known Activations