© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 195903
    Prev
    Next
    INDEX
    Explanations

    GPT

    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_9_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
    ك
    1.46
    ка
    1.25
    ่
    1.13
    кает
    0.99
    يره
    0.97
    로
    0.93
    يب
    0.87
    {
    0.86
    ม
    0.84
    يف
    0.84
    POSITIVE LOGITS
    on
    1.50
    h
    1.41
    al
    1.34
    y
    1.21
    s
    1.18
    man
    1.12
    is
    1.06
    س
    1.06
    to
    1.03
    am
    1.02
    Activations Density 0.022%

    No Known Activations