© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214604
    Prev
    Next
    INDEX
    Explanations

    аспект

    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_5_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
    t
    2.03
    де
    1.38
    z
    1.29
    l
    1.27
    x
    1.26
    c
    1.24
    D
    1.23
    ми
    1.13
    G
    1.09
    ec
    1.09
    POSITIVE LOGITS
    স
    1.46
    :
    1.32
    م
    1.23
    د
    1.21
    ன்
    1.19
    ة
    1.14
    ส
    1.14
    ور
    1.11
    1.10
    ل
    1.10
    Activations Density 0.000%

    No Known Activations