© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59964
    Prev
    Next
    INDEX
    Explanations

    DAW (Digital Audio Workstation)

    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_2_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
     for
    1.48
     I
    1.35
     U
    1.33
     S
    1.30
     L
    1.27
     K
    1.17
     T
    1.16
    for
    1.16
     F
    1.09
     can
    1.09
    POSITIVE LOGITS
     χρήση
    1.45
    人
    1.36
    ка
    1.30
    ها
    1.28
     θέση
    1.24
     μία
    1.23
    ನ
    1.20
    การ
    1.19
    ના
    1.18
    ként
    1.16
    Activations Density 0.000%

    No Known Activations