© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75768
    Prev
    Next
    INDEX
    Explanations

    Elara

    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_31_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
    確
    0.30
     headline
    0.28
     household
    0.28
     fogo
    0.28
    cul
    0.27
    IDGE
    0.27
     testimony
    0.27
     [])
    0.27
    headline
    0.27
    }^{+
    0.27
    POSITIVE LOGITS
     मृतक
    0.29
     deceased
    0.29
    生成的
    0.29
     Deepak
    0.28
     bequeathed
    0.28
     falleció
    0.28
     मृतकों
    0.28
     مرحوم
    0.27
     मरने
    0.27
    Stephen
    0.27
    Activations Density 0.002%

    No Known Activations