© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33489
    Prev
    Next
    INDEX
    Explanations

    phrases with punctuation

    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_31_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
     '}';
    0.40
    abá
    0.39
     infusions
    0.37
    DbType
    0.37
     연결
    0.36
    ぅ
    0.36
    虺
    0.35
     convolutions
    0.35
    ༡
    0.34
    連接
    0.34
    POSITIVE LOGITS
     identiques
    0.36
    sop
    0.35
    ghis
    0.33
     sopr
    0.33
    LLING
    0.33
    format
    0.33
     ơn
    0.33
     bundan
    0.33
     վ
    0.33
     किए
    0.32
    Activations Density 0.000%

    No Known Activations