© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90044
    Prev
    Next
    INDEX
    Explanations

    Understood period

    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_11_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
     cak
    0.64
     яка
    0.60
     LY
    0.57
    ਦੀ
    0.57
     hepat
    0.56
     jauh
    0.56
     pel
    0.55
     ț
    0.55
     anharmonic
    0.55
     sequential
    0.54
    POSITIVE LOGITS
    ية
    0.70
    劻
    0.68
     कालेज
    0.67
    nement
    0.65
    stellungen
    0.64
    k
    0.63
    zhou
    0.63
     Alegre
    0.62
     सेवाएं
    0.59
    色的
    0.59
    Activations Density 0.008%

    No Known Activations