© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139059
    Prev
    Next
    INDEX
    Explanations

    India and related history

    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
    ۔
    0.59
     distract
    0.52
    m
    0.52
    in
    0.51
     payday
    0.51
    e
    0.50
     right
    0.50
     Ahead
    0.50
     significa
    0.49
     ahead
    0.49
    POSITIVE LOGITS
     également
    0.50
    ței
    0.49
    洖
    0.49
    })]
    0.48
     bör
    0.48
    佳
    0.48
     guérir
    0.47
    ischer
    0.46
     பரி
    0.46
     localized
    0.45
    Activations Density 0.000%

    No Known Activations