© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38534
    Prev
    Next
    INDEX
    Explanations

    stock management

    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_11_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
     حتى
    0.61
     ☐
    0.61
    RL
    0.59
    IN
    0.59
     على
    0.57
     អ
    0.55
     направи
    0.55
    ávají
    0.54
    BL
    0.54
     للح
    0.54
    POSITIVE LOGITS
    compassing
    0.65
     hommage
    0.57
     t
    0.56
     innovations
    0.55
    同样的
    0.54
     Announcements
    0.54
     Instance
    0.54
     आरोपों
    0.54
     Symbolic
    0.53
     delimiters
    0.53
    Activations Density 0.001%

    No Known Activations