© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165252
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by nouns/pronouns

    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
    es
    0.54
    ي
    0.52
    机遇
    0.47
    従来の
    0.47
    寻求
    0.47
    KeyPressed
    0.47
    slider
    0.46
    league
    0.46
    取り組み
    0.46
    ი
    0.46
    POSITIVE LOGITS
     Schwab
    0.57
     dat
    0.53
    öre
    0.53
    zaam
    0.52
    ahaan
    0.52
     этот
    0.51
    olge
    0.51
     Schmidt
    0.50
     sabbam
    0.50
     jste
    0.50
    Activations Density 0.017%

    No Known Activations