© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2019
    Prev
    Next
    INDEX
    Explanations

    surgical procedures techniques

    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_39_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
     enunciado
    0.40
    ्सा
    0.38
     '*'
    0.38
    陖
    0.36
     auditors
    0.35
    集成
    0.35
    кої
    0.34
     Ebert
    0.34
     Krankheit
    0.34
    㕩
    0.34
    POSITIVE LOGITS
     techniques
    0.55
     technik
    0.53
     teknik
    0.50
     Teknik
    0.50
     техники
    0.50
     technically
    0.50
     Techniques
    0.49
    Techn
    0.48
     atra
    0.48
     técnicas
    0.47
    Activations Density 0.086%

    No Known Activations