© 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. 32697
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
    ateur
    0.86
    ateurs
    0.81
    teur
    0.79
    iteur
    0.70
     A
    0.70
    ieu
    0.65
    teurs
    0.63
    iteurs
    0.61
    eur
    0.61
    teau
    0.54
    POSITIVE LOGITS
     torso
    0.40
    сора
    0.38
    торы
    0.36
    ጋ
    0.36
     Thor
    0.35
     அவ்வ
    0.35
    妿
    0.35
    悉
    0.35
     egent
    0.35
    是否存在
    0.35
    Activations Density 0.013%

    No Known Activations