© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120332
    Prev
    Next
    INDEX
    Explanations

    places or geographical entities

    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_27_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
    𝗱
    0.46
     ಮಾಡಿದ್ದಾರೆ
    0.44
     범위
    0.42
    듯이
    0.41
    riminate
    0.40
     yattha
    0.39
    墮
    0.38
     הם
    0.38
     élevées
    0.38
     estão
    0.38
    POSITIVE LOGITS
    City
    0.41
    Many
    0.40
     City
    0.39
     Negoti
    0.36
     Conduit
    0.36
     Planet
    0.35
     ditch
    0.35
    nog
    0.35
     заду
    0.34
    desk
    0.34
    Activations Density 0.000%

    No Known Activations