© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17758
    Prev
    Next
    INDEX
    Explanations

    MEAL, M&E, Monitoring, Evaluation

    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_34_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
     escánd
    0.44
     revista
    0.38
    issory
    0.38
    ://"
    0.38
     revistas
    0.38
    Crossing
    0.37
    })"
    0.37
     (#{
    0.37
     अटेम्प्ट
    0.37
     administrador
    0.37
    POSITIVE LOGITS
     targets
    0.44
    种子
    0.42
     Targets
    0.40
     Yamaha
    0.40
     sisters
    0.38
     target
    0.38
     Seeds
    0.38
     par
    0.37
     फ्रेंड्स
    0.36
     wildlife
    0.36
    Activations Density 0.002%

    No Known Activations