© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 236103
    Prev
    Next
    INDEX
    Explanations

    scientific or technical context

    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_46_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
     सिंध
    0.41
    rypsin
    0.39
    銮
    0.38
     কূপ
    0.36
    ของคุณ
    0.36
    眹
    0.36
     przes
    0.36
    抽出
    0.36
    ွန်
    0.35
    挝
    0.35
    POSITIVE LOGITS
     ex
    0.70
     Ex
    0.59
    Ex
    0.56
     eks
    0.48
     Exo
    0.46
     EXO
    0.45
     экс
    0.42
    ex
    0.42
     exo
    0.42
     exer
    0.41
    Activations Density 0.000%

    No Known Activations