© 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. 12139
    Prev
    Next
    INDEX
    Explanations

    weather, actions, greetings

    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
    0.25
     acute
    0.24
     аку
    0.24
    Microsoft
    0.21
     konserv
    0.21
    !
    0.21
     diuretic
    0.21
    -
    0.21
    2
    0.21
     •
    0.20
    POSITIVE LOGITS
    രാ
    0.28
    ́p
    0.27
    він
    0.26
    startY
    0.26
     Tvam
    0.26
    ｑ
    0.26
    鿁
    0.26
    layan
    0.25
     রিজ
    0.25
     সংখ্যাগ
    0.25
    Activations Density 0.061%

    No Known Activations