© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9290
    Prev
    Next
    INDEX
    Explanations

    có khỏe không?

    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_13_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
    س
    0.23
    вах
    0.21
     disconnecting
    0.20
    이지만
    0.20
    сё
    0.20
    스가
    0.20
    нах
    0.19
     أخرى
    0.19
    스는
    0.19
     guarded
    0.19
    POSITIVE LOGITS
    o
    0.25
    q
    0.22
    u
    0.21
    Q
    0.20
    ע
    0.19
    つい
    0.18
    en
    0.18
    Pi
    0.18
     berusaha
    0.18
    esti
    0.18
    Activations Density 0.002%

    No Known Activations