© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229811
    Prev
    Next
    INDEX
    Explanations

    thrombocytes, thrombotic, thrombopoietin

    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_6_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
    t
    1.43
    ت
    0.91
    l
    0.88
    a
    0.81
    其他
    0.78
    n
    0.77
    tiden
    0.74
    r
    0.74
    name
    0.72
    ről
    0.71
    POSITIVE LOGITS
     says
    0.64
    ணை
    0.64
     habeas
    0.61
     penal
    0.61
     cose
    0.60
     cereal
    0.59
     eukaryotic
    0.58
     bosque
    0.58
    انی
    0.57
    ัด
    0.56
    Activations Density 0.000%

    No Known Activations