© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 146134
    Prev
    Next
    INDEX
    Explanations

    Вот несколько / основные / список

    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_0_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
    x
    1.95
    و
    1.49
    c
    1.39
    ir
    1.27
    ारा
    1.26
    on
    1.20
    ému
    1.20
     insign
    1.20
    cje
    1.16
    隐含规则
    1.16
    POSITIVE LOGITS
    '
    2.05
    в
    1.36
    -
    1.23
    اي
    1.19
    न
    1.16
    з
    1.16
    '/>
    1.14
    Part
    1.13
    ۔
    1.13
    מ
    1.11
    Activations Density 0.000%

    No Known Activations