© 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. 10154
    Prev
    Next
    INDEX
    Explanations

    strong nuclear force

    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
    ını
    0.58
    name
    0.52
     mesaj
    0.52
    IA
    0.51
    ီ
    0.49
    وری
    0.47
    mathrm
    0.47
    ının
    0.45
    ৭০
    0.45
     yardımcı
    0.45
    POSITIVE LOGITS
    ล
    0.52
    elung
    0.46
    icates
    0.46
     уси
    0.46
    л
    0.45
     comedies
    0.45
    σι
    0.44
    Shin
    0.44
     académ
    0.44
    onk
    0.44
    Activations Density 0.001%

    No Known Activations