© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172244
    Prev
    Next
    INDEX
    Explanations

    if not more / best

    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_20_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
     डायरेक्शन
    0.42
    ้อง
    0.42
    ายเป็น
    0.42
    ект
    0.41
    ર્થ
    0.41
    หัส
    0.41
     usernames
    0.41
     l
    0.40
    тного
    0.39
    全程
    0.38
    POSITIVE LOGITS
    АТ
    0.51
     tamaño
    0.51
    一定要
    0.49
    bedingungen
    0.48
     asegurarse
    0.48
    Если
    0.48
     entender
    0.47
    Ε
    0.47
    CON
    0.46
    PPE
    0.46
    Activations Density 0.000%

    No Known Activations