© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4110
    Prev
    Next
    INDEX
    Explanations

    conjunctions and punctuation separators

    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_40_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
    might
    0.42
     falla
    0.41
    stated
    0.40
     youll
    0.38
    }]}\
    0.37
     jeste
    0.37
    liches
    0.37
    مال
    0.36
    authors
    0.36
     theyre
    0.36
    POSITIVE LOGITS
     Suzhou
    0.43
     Qing
    0.38
    zhihu
    0.38
     UU
    0.38
     ①
    0.38
     جمهوری
    0.38
     Qiu
    0.38
    ং
    0.37
    ——
    0.36
    aturally
    0.36
    Activations Density 0.009%

    No Known Activations