© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 33403
    Prev
    Next
    INDEX
    Explanations

    or

    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_50_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
    žia
    0.38
    avelin
    0.38
    absValue
    0.36
    ointees
    0.36
    Things
    0.35
    ጪ
    0.34
    aporte
    0.34
    things
    0.33
     الوط
    0.33
    usting
    0.33
    POSITIVE LOGITS
     or
    1.64
    หรือ
    1.58
    或
    1.58
     или
    1.57
     அல்லது
    1.44
     hoặc
    1.38
     বা
    1.34
     ಅಥವಾ
    1.33
     또는
    1.31
     અથવા
    1.27
    Activations Density 0.006%

    No Known Activations