© 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. 31399
    Prev
    Next
    INDEX
    Explanations

    african

    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
     chops
    0.53
    źdz
    0.41
     chop
    0.41
    겹
    0.40
     neod
    0.38
     guardian
    0.38
    টসঅ্যাপ
    0.38
     pudieron
    0.38
    ĕç
    0.38
     چ
    0.38
    POSITIVE LOGITS
     wei
    0.47
    am
    0.41
    UnifiedTopology
    0.41
    weaving
    0.39
     heur
    0.38
     weave
    0.37
    ওয়ে
    0.37
    GO
    0.36
    man
    0.35
     whey
    0.35
    Activations Density 0.010%

    No Known Activations