© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 213490
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    knit
    0.40
    outez
    0.39
    un
    0.38
     ण
    0.37
    মি
    0.37
    ruit
    0.37
    hd
    0.37
    нуть
    0.36
    aso
    0.36
    rukt
    0.36
    POSITIVE LOGITS
     posing
    0.37
    VERTISING
    0.37
     sulphur
    0.37
     charging
    0.35
     عدم
    0.34
    Spy
    0.33
     ຊ
    0.33
     fate
    0.33
    㳒
    0.33
    Percentages
    0.32
    Activations Density 0.004%

    No Known Activations