© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116765
    Prev
    Next
    INDEX
    Explanations

    greetings in multiple languages

    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_27_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
     réaliser
    0.46
    ciphertext
    0.43
    SwapChain
    0.43
    鸴
    0.43
    Hons
    0.43
    实施
    0.42
    ravenous
    0.42
     crystallography
    0.41
    ="'$(
    0.40
     exposureButton
    0.40
    POSITIVE LOGITS
     geçen
    0.39
     صدر
    0.38
     Tort
    0.36
     vys
    0.35
     selten
    0.34
    ised
    0.33
     sag
    0.33
     சரா
    0.33
    size
    0.33
     مف
    0.33
    Activations Density 0.002%

    No Known Activations