© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 98156
    Prev
    Next
    INDEX
    Explanations

    million years ago

    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_14_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
    жа
    0.50
    Hydrochloride
    0.49
    Ronald
    0.48
    傈
    0.48
     ഇഷ്ട
    0.48
    mult
    0.47
     Акысыз
    0.47
    дру
    0.46
    Bool
    0.46
    featuresMatrix
    0.46
    POSITIVE LOGITS
     of
    0.59
     Parks
    0.56
    ى
    0.48
     between
    0.47
     Carnival
    0.46
     taver
    0.45
     comun
    0.45
     carnival
    0.44
     Carb
    0.44
     in
    0.44
    Activations Density 0.000%

    No Known Activations