© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166556
    Prev
    Next
    INDEX
    Explanations

    config settings options

    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_31_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
    太多
    0.41
     ኢ
    0.39
     Polonia
    0.39
    牫
    0.38
     suffered
    0.38
     विश्वास
    0.38
     Eduard
    0.38
     Tata
    0.38
     घायल
    0.36
     unprepared
    0.35
    POSITIVE LOGITS
     CURLOPT
    0.38
    光源
    0.37
    Forg
    0.36
    🧁
    0.36
     addSubview
    0.36
    ệm
    0.35
    INGER
    0.35
    inger
    0.35
     curric
    0.34
     digitalWrite
    0.34
    Activations Density 0.000%

    No Known Activations