© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    4. 208544
    Prev
    Next
    INDEX
    Explanations

    genetic sequences and genomic analysis

    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_20_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
    ইতি
    0.46
     ಔಷಧ
    0.45
    SBS
    0.43
    fromString
    0.43
    Schwarz
    0.43
    BOUND
    0.42
     ES
    0.41
    喍
    0.40
    বহ
    0.40
    Bou
    0.40
    POSITIVE LOGITS
     fermion
    0.46
    ్రీ
    0.44
     maiden
    0.43
    ertown
    0.43
    empot
    0.43
     no
    0.42
     維尼
    0.42
     timely
    0.41
    irthday
    0.41
     funeral
    0.41
    Activations Density 0.000%

    No Known Activations