© 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. 13957
    Prev
    Next
    INDEX
    Explanations

    let's just say

    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
     Приступљено
    0.52
     seulement
    0.50
     வெளியாக
    0.49
     refuge
    0.48
     preparação
    0.48
     refug
    0.47
    Ⲁ
    0.47
     كما
    0.46
     Hö
    0.46
     precum
    0.46
    POSITIVE LOGITS
    i
    0.61
    。
    0.57
    േറ്റ
    0.52
     sprints
    0.51
    User
    0.50
    ಿಕೆ
    0.50
    okens
    0.50
    Force
    0.49
    嫒
    0.49
    iped
    0.48
    Activations Density 0.004%

    No Known Activations