© 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. 152618
    Prev
    Next
    INDEX
    Explanations

    science and scientists

    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
    Maya
    0.41
     دسترس
    0.33
    Inn
    0.33
     retra
    0.32
     Maya
    0.32
    প্রসঙ্গত
    0.32
    ✂
    0.31
     ह
    0.31
    ຄ້າ
    0.31
     Inns
    0.30
    POSITIVE LOGITS
     investigating
    0.35
     investigate
    0.34
     anatomical
    0.34
     investigar
    0.34
     almond
    0.32
     پزشکی
    0.31
     investigates
    0.31
     анато
    0.30
     जांच
    0.29
     embry
    0.29
    Activations Density 0.037%

    No Known Activations