© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 178909
    Prev
    Next
    INDEX
    Explanations

    IN

    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
    阳
    0.47
    陽
    0.41
    ymers
    0.39
     방법에
    0.38
     ext
    0.37
     Rit
    0.37
    EDED
    0.37
     உரிய
    0.36
     slowdown
    0.36
    desIP
    0.36
    POSITIVE LOGITS
    ੍ਹਾਂ
    0.46
    agg
    0.43
    Agg
    0.39
    嬙
    0.38
     cinquième
    0.38
    泻
    0.38
    aggressive
    0.36
    そこで
    0.36
     路
    0.36
    ཆ
    0.36
    Activations Density 0.010%

    No Known Activations