© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130907
    Prev
    Next
    INDEX
    Explanations

    melatonin, AANAT, Arabic numerals, Vaadin

    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_1_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
     It
    1.45
    a
    1.23
     for
    1.18
     ayudar
    1.13
     dona
    1.13
     be
    1.09
     can
    1.09
     fonctionner
    1.09
     présente
    1.08
    i
    1.07
    POSITIVE LOGITS
    3
    1.41
    ز
    1.29
    ла
    1.27
    iv
    1.26
    ために
    1.26
    li
    1.25
    ため
    1.24
    ためには
    1.21
    لة
    1.20
    在
    1.20
    Activations Density 0.000%

    No Known Activations