© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 141611
    Prev
    Next
    INDEX
    Explanations

    City

    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
     ноги
    0.42
    懋
    0.41
    भाज
    0.40
     đỉnh
    0.39
    Center
    0.38
    ICENSE
    0.38
    ऱ्यांना
    0.36
    liğini
    0.36
    𝗕
    0.36
    ഗ്രഹം
    0.36
    POSITIVE LOGITS
     City
    0.43
    City
    0.42
     সাহিত্য
    0.40
    市立
    0.40
    flask
    0.39
     Substitution
    0.38
    ecd
    0.38
     CITY
    0.37
     sred
    0.36
    scopes
    0.36
    Activations Density 0.004%

    No Known Activations