© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117468
    Prev
    Next
    INDEX
    Explanations

    numerical input from user

    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
    駐
    0.40
    媒體
    0.39
    CHREIB
    0.38
     territory
    0.38
     médias
    0.38
     start
    0.38
    media
    0.38
     parler
    0.37
    checkBox
    0.37
     teléfono
    0.37
    POSITIVE LOGITS
    ozat
    0.40
    umma
    0.39
     తీసుకొ
    0.39
    纍
    0.39
     dataGenerator
    0.38
     Peptide
    0.38
    iverse
    0.38
     메소
    0.38
     parametrization
    0.38
    osum
    0.38
    Activations Density 0.002%

    No Known Activations