© 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. 35551
    Prev
    Next
    INDEX
    Explanations

    qualifications, experience, strong proficiency

    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
     homogeneity
    0.38
    大規模
    0.38
    Arizona
    0.38
     Roja
    0.38
    ﻲ
    0.38
     تبقى
    0.37
    ጼ
    0.37
     RJ
    0.36
    霹
    0.36
    onomy
    0.35
    POSITIVE LOGITS
     охла
    0.46
    eller
    0.39
     причине
    0.39
    onavírus
    0.37
     fun
    0.36
    bindingNavigator
    0.36
    乐趣
    0.35
    logfile
    0.35
     phù
    0.35
     Tür
    0.35
    Activations Density 0.001%

    No Known Activations