© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134162
    Prev
    Next
    INDEX
    Explanations

    weather location codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_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
    PDA
    0.39
    entertain
    0.38
    Zig
    0.37
     enrolled
    0.35
    眹
    0.35
    PhotoImage
    0.35
    compart
    0.35
    الہ
    0.35
     compartments
    0.35
    نف
    0.34
    POSITIVE LOGITS
     QSO
    0.78
     QSOs
    0.77
     DX
    0.61
    activating
    0.53
     Q
    0.52
    DX
    0.52
     dx
    0.52
     Calls
    0.51
     calls
    0.49
    Locator
    0.48
    Activations Density 0.009%

    No Known Activations