© 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
    2. Gemma-3-27B-IT
    3. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 36467
    Prev
    Next
    INDEX
    Explanations

    say "hand" words

    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
    രുവ
    0.42
     cherished
    0.38
     firewall
    0.35
    وترات
    0.34
    အပိုင်း
    0.34
    عهد
    0.34
    ကာ
    0.33
     ඔ
    0.33
    ruppe
    0.33
    ленні
    0.33
    POSITIVE LOGITS
     hand
    2.53
    Hand
    2.27
     Hand
    2.20
    hand
    2.16
     HAND
    2.08
    手
    1.97
    HAND
    1.94
     손
    1.65
    손
    1.61
     hånd
    1.58
    Activations Density 0.009%

    No Known Activations