© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 58423
    Prev
    Next
    INDEX
    Explanations

    numbers and references

    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_59_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
    trex
    0.44
     hairc
    0.43
    ("@
    0.42
    acre
    0.41
     quanta
    0.40
     జమ
    0.40
     audiobook
    0.40
    ysc
    0.38
     kilobytes
    0.38
     senti
    0.38
    POSITIVE LOGITS
     A
    0.42
    
    0.42
    这类
    0.41
    सं
    0.40
    ১৮
    0.39
    番号
    0.39
     B
    0.38
    们的
    0.38
    당
    0.38
    们
    0.37
    Activations Density 0.000%

    No Known Activations