© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10925
    Prev
    Next
    INDEX
    Explanations

    consulate and consular section

    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
    Quadrant
    0.57
    に行く
    0.55
     আৰ
    0.50
    =")"
    0.48
    ísmo
    0.47
    ismo
    0.47
     O
    0.47
     पार्वती
    0.46
     Ovo
    0.46
    原来的
    0.46
    POSITIVE LOGITS
     huz
    0.59
    _{
    0.58
    br
    0.57
    +
    0.57
     difficulties
    0.57
    standards
    0.57
     muon
    0.55
    ک
    0.55
    necess
    0.55
    澼
    0.54
    Activations Density 0.000%

    No Known Activations