© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109895
    Prev
    Next
    INDEX
    Explanations

    protoyping

    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
    ד
    1.47
    ן
    1.20
    י
    1.19
    ס
    1.03
    تون
    1.02
    ל
    0.99
    ۰
    0.98
    (
    0.97
     некоторое
    0.96
    ו
    0.93
    POSITIVE LOGITS
    S
    1.57
    O
    1.37
    の
    1.34
    IR
    1.27
    L
    1.24
    ER
    1.22
    OT
    1.20
    US
    1.17
    E
    1.16
    し
    1.16
    Activations Density 0.001%

    No Known Activations