© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 86071
    Prev
    Next
    INDEX
    Explanations

    coins, selection, titles, library, sport coverage

    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_23_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
     alimentar
    0.33
    mouseup
    0.31
     episodi
    0.31
     মজুদ
    0.30
    FhirExtension
    0.30
     fertilized
    0.29
     yeux
    0.29
    ᔭ
    0.29
     انك
    0.28
     positrons
    0.28
    POSITIVE LOGITS
    ्यास
    0.30
    es
    0.30
    enames
    0.29
     વિવિધ
    0.29
     rambling
    0.28
    yl
    0.28
     விதி
    0.28
     Acá
    0.28
     ramb
    0.27
     бер
    0.27
    Activations Density 0.001%

    No Known Activations