© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 149984
    Prev
    Next
    INDEX
    Explanations

    a

    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
     a
    0.55
     Variable
    0.41
    ot
    0.39
     dedos
    0.39
     variable
    0.38
    a
    0.38
     Life
    0.37
    types
    0.37
     Letters
    0.36
     .
    0.36
    POSITIVE LOGITS
    表中
    0.41
    rawl
    0.39
    Plain
    0.39
    ట్‌లో
    0.39
    გრამ
    0.38
    Gravestone
    0.38
    Nonce
    0.38
     प्लॉट
    0.37
     سایټ
    0.37
    Paper
    0.36
    Activations Density 0.007%

    No Known Activations