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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 16697
    Prev
    Next
    INDEX
    Explanations

    cannot provide medical or financial advice

    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_34_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
    зонта
    0.42
     посвящен
    0.38
    antu
    0.38
    蝸
    0.38
    idu
    0.36
    وي
    0.36
    Celula
    0.36
    idung
    0.35
     McLaughlin
    0.35
    isseur
    0.35
    POSITIVE LOGITS
     পরিস্থিত
    0.41
     debat
    0.38
    )+'
    0.38
    ранд
    0.38
    +[
    0.37
    pul
    0.37
    情况
    0.37
     unlabeled
    0.37
     vt
    0.36
    гите
    0.36
    Activations Density 0.003%

    No Known Activations