© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158195
    Prev
    Next
    INDEX
    Explanations

    ms, M, mi

    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_2_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
    m
    1.52
    p
    1.39
    ne
    1.34
    1.28
    i
    1.19
    l
    1.13
    with
    1.10
    d
    1.08
    st
    1.07
    s
    1.06
    POSITIVE LOGITS
    ка
    1.71
    ки
    1.52
    ால்
    1.45
    ли
    1.44
    ра
    1.43
    ле
    1.38
    р
    1.36
    ла
    1.30
    д
    1.27
    اری
    1.25
    Activations Density 0.000%

    No Known Activations