© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 17453
    Prev
    Next
    INDEX
    Explanations

    vector graphics

    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_15_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
    し
    0.27
     ناخد
    0.26
    d
    0.26
     відбувається
    0.26
     acontece
    0.26
    ен
    0.25
     електри
    0.25
    f
    0.25
    bef
    0.25
    騙
    0.25
    POSITIVE LOGITS
     Pesh
    0.27
     Wochschr
    0.27
     মোত
    0.26
     finca
    0.26
     পরিণতি
    0.26
    Ǧ
    0.26
     виде
    0.25
     வார்த்த
    0.25
     paparazzi
    0.25
    秞
    0.25
    Activations Density 0.010%

    No Known Activations