© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 68907
    Prev
    Next
    INDEX
    Explanations

    Shanghai

    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_46_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
     Hond
    0.41
     Noz
    0.40
    γραμμα
    0.39
    ประส
    0.39
    铍
    0.37
     जाट
    0.37
    OrCallback
    0.36
     Вин
    0.36
    Dart
    0.35
    വിത
    0.35
    POSITIVE LOGITS
     Shanghai
    2.31
    Shanghai
    2.22
    上海
    2.08
     shang
    2.06
     Shang
    1.98
    Shang
    1.85
     上海
    1.77
    沪
    1.28
    滬
    1.27
     SH
    1.20
    Activations Density 0.020%

    No Known Activations