© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 198663
    Prev
    Next
    INDEX
    Explanations

    install ntp

    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_15_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
    ivis
    0.55
    /
    0.53
    odim
    0.52
     ,
    0.52
    ivi
    0.52
    BMW
    0.50
    ad
    0.49
    modes
    0.48
    .,
    0.48
     coupons
    0.47
    POSITIVE LOGITS
     πρό
    0.67
    𝟘
    0.64
    通信
    0.58
     Ні
    0.58
     Cardi
    0.58
     yǔ
    0.57
     Пример
    0.57
    ５
    0.57
     Ска
    0.57
    आईएस
    0.57
    Activations Density 0.002%

    No Known Activations