© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 4393
    Prev
    Next
    INDEX
    Explanations

    months and days

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
    Ƣ
    0.43
    pples
    0.38
     πα
    0.34
     উচিৎ
    0.34
     ਜਾ
    0.33
    ITURE
    0.33
     Extract
    0.33
    őz
    0.33
    Ư
    0.33
    ಗಳಿಂದ
    0.32
    POSITIVE LOGITS
    flops
    0.42
    else
    0.41
     deoxy
    0.40
     அறு
    0.39
     leukemia
    0.38
     sez
    0.38
    प्पो
    0.38
     deuterium
    0.37
     begon
    0.37
     zippers
    0.37
    Activations Density 0.002%

    No Known Activations