© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 198536
    Prev
    Next
    INDEX
    Explanations

    Dragon

    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
    㫜
    0.44
     attaching
    0.41
     Kxa
    0.39
    riol
    0.39
     policing
    0.39
    adec
    0.38
    хов
    0.38
    wię
    0.37
     locksmith
    0.37
    珣
    0.37
    POSITIVE LOGITS
    শিপ
    0.39
     夕
    0.38
    utz
    0.38
    umbers
    0.38
    ಝ
    0.38
    aturas
    0.38
    owne
    0.37
    auer
    0.37
     तु
    0.36
    ちに
    0.36
    Activations Density 0.002%

    No Known Activations