© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 198529
    Prev
    Next
    INDEX
    Explanations

    Serbian and Balkan phrases

    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_12_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
    ()));
    0.51
    𝓂
    0.50
    ℗
    0.48
    COLOR
    0.48
    bez
    0.47
    oasis
    0.47
    呼ば
    0.46
    ウォ
    0.46
    lebih
    0.46
    ².
    0.46
    POSITIVE LOGITS
     turbine
    0.58
     resembling
    0.57
     resemble
    0.55
     aspirated
    0.52
     arriving
    0.51
     ktorí
    0.51
     branch
    0.50
     Annie
    0.50
    APs
    0.50
     arrivals
    0.49
    Activations Density 0.000%

    No Known Activations