© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242937
    Prev
    Next
    INDEX
    Explanations

    hugely popular or diverse

    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_40_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
     satisfaction
    0.42
    腑
    0.41
     почти
    0.41
    запа
    0.41
     satisfacción
    0.40
     удовлетво
    0.40
    幾乎
    0.39
    satisf
    0.38
     만족
    0.38
     almost
    0.37
    POSITIVE LOGITS
     Retrieval
    0.39
    гії
    0.39
    DatePicker
    0.39
     POA
    0.39
     Location
    0.38
    лад
    0.38
    虍
    0.38
     luogo
    0.37
    Lad
    0.37
     calendrier
    0.36
    Activations Density 0.007%

    No Known Activations