© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196578
    Prev
    Next
    INDEX
    Explanations

    recent

    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_27_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
    および
    0.36
    っぽい
    0.31
    தமான
    0.30
    ゜
    0.30
    薙
    0.30
    dozen
    0.29
    üglich
    0.29
    hnung
    0.29
    UOUS
    0.29
    均
    0.29
    POSITIVE LOGITS
     alto
    0.37
    erville
    0.33
     Bi
    0.32
     приблизи
    0.32
    代言
    0.32
     förs
    0.32
     recientes
    0.32
     indo
    0.31
     teritor
    0.30
     bior
    0.30
    Activations Density 0.000%

    No Known Activations