© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 101039
    Prev
    Next
    INDEX
    Explanations

    Anglo-Saxon England

    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_14_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
    шена
    0.43
     брать
    0.42
    珞
    0.42
    <0xA8>
    0.41
     vestib
    0.41
     TNFR
    0.41
    桐
    0.40
    عو
    0.39
     silber
    0.38
     திருக்கோ
    0.38
    POSITIVE LOGITS
     Vậy
    0.44
    x
    0.42
    igere
    0.42
    t
    0.42
    W
    0.41
    vature
    0.41
    v
    0.40
    é
    0.40
    ON
    0.39
    isar
    0.39
    Activations Density 0.001%

    No Known Activations