© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144753
    Prev
    Next
    INDEX
    Explanations

    ED followed by P, L, M, or S

    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_0_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
    ۔
    1.71
    is
    1.59
    एस
    1.55
    지
    1.52
     incisions
    1.49
     ductility
    1.47
    ی
    1.41
    to
    1.40
    та
    1.38
    ༦
    1.33
    POSITIVE LOGITS
    و
    1.27
    ö
    1.27
    رت
    1.20
    ad
    1.19
    గ
    1.18
    我
    1.16
    ના
    1.13
    lauf
    1.10
    ড
    1.10
    iss
    1.07
    Activations Density 0.000%

    No Known Activations