© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79102
    Prev
    Next
    INDEX
    Explanations

    Artificial Neural Network (ANN) and kubectl

    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_0_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
    ب
    1.86
    ي
    1.72
    q
    1.51
    지
    1.43
    d
    1.41
    ,
    1.41
    ла
    1.39
    h
    1.39
    ۰
    1.38
    ర్
    1.30
    POSITIVE LOGITS
    ıları
    1.50
     oub
    1.26
     acides
    1.23
    ьте
    1.21
     énorm
    1.15
     organis
    1.13
    ların
    1.11
     enferm
    1.11
    ativa
    1.10
     malades
    1.09
    Activations Density 0.000%

    No Known Activations