© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106258
    Prev
    Next
    INDEX
    Explanations

    India

    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_1_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
    quela
    1.17
    ก็
    1.13
     ότι
    1.09
     그다음에
    1.07
    न
    1.07
    that
    1.06
     שה
    1.06
     maksymal
    1.00
    ພວກເຮົາ
    0.99
     that
    0.98
    POSITIVE LOGITS
    ien
    1.05
    ни
    0.99
    A
    0.91
    _
    0.91
    }
    0.90
    de
    0.90
    ern
    0.89
    in
    0.88
    ill
    0.85
    ెంట్
    0.85
    Activations Density 0.001%

    No Known Activations