© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 32625
    Prev
    Next
    INDEX
    Explanations

    standing

    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
    决
    0.42
    ⊗
    0.39
    球面
    0.37
    MLS
    0.37
    чь
    0.36
     क्रिस्ट
    0.36
    deren
    0.36
    жному
    0.35
     berl
    0.35
    结
    0.35
    POSITIVE LOGITS
     стоя
    0.67
     standing
    0.63
     Standing
    0.59
    Standing
    0.50
     pou
    0.50
     bổ
    0.47
     berdiri
    0.46
     सार
    0.44
     Pou
    0.43
    standing
    0.43
    Activations Density 0.013%

    No Known Activations