© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 2100
    Prev
    Next
    INDEX
    Explanations

    native speakers and tutors

    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_38_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
     총
    0.43
     Де
    0.40
     DE
    0.39
     WLAN
    0.39
     অন্তর্গত
    0.39
     второй
    0.38
     самое
    0.38
     оказыва
    0.37
    家居
    0.37
     Tổng
    0.37
    POSITIVE LOGITS
     language
    0.47
    language
    0.44
     top
    0.43
    ivy
    0.41
     curated
    0.40
    ualitas
    0.39
    mvn
    0.39
    語
    0.38
     livery
    0.38
    inge
    0.37
    Activations Density 0.001%

    No Known Activations