© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43600
    Prev
    Next
    INDEX
    Explanations

    extracting characteristic values

    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_13_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
    トヨタ
    0.44
     arrogant
    0.44
     Furious
    0.43
     Attendees
    0.43
    manirrahim
    0.43
    땐
    0.43
     maatau
    0.42
     yö
    0.42
    ಲ್
    0.41
    jell
    0.41
    POSITIVE LOGITS
     seno
    0.45
    กว่า
    0.44
     než
    0.42
     ఆల
    0.42
     Hl
    0.41
     مكان
    0.40
     ослож
    0.40
    她们
    0.39
    ;"
    0.39
     пита
    0.38
    Activations Density 0.010%

    No Known Activations