© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106298
    Prev
    Next
    INDEX
    Explanations

    pot ajudar

    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_1_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
    ב
    1.32
    to
    1.25
     be
    1.24
    ำ
    1.23
     in
    1.22
    在
    1.22
    м
    1.18
    ként
    1.02
    開始
    0.99
     was
    0.98
    POSITIVE LOGITS
    :
    1.67
    ot
    1.28
    ak
    1.26
    ہ
    1.14
    4
    1.13
    8
    1.13
    ang
    1.12
    O
    1.12
    Z
    1.10
    UM
    1.08
    Activations Density 0.000%

    No Known Activations