© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137145
    Prev
    Next
    INDEX
    Explanations

    Danish locations

    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_12_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
    дован
    0.54
    ዘጋ
    0.51
    塹
    0.49
     legitim
    0.47
    ढ़ाई
    0.47
     coherent
    0.47
    ка
    0.46
    дови
    0.46
    се
    0.45
     incentiv
    0.45
    POSITIVE LOGITS
    ”:
    0.47
    ang
    0.46
    .”)
    0.45
     হইয়৷
    0.43
    entum
    0.43
    .”
    0.43
     дві
    0.43
     zda
    0.42
    锛
    0.42
    InBuffer
    0.42
    Activations Density 0.000%

    No Known Activations