© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 66142
    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_51_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
    山田
    0.40
    Assets
    0.39
     rispond
    0.39
     Multipart
    0.39
    沓
    0.39
    FOCUS
    0.39
    respond
    0.38
    मु
    0.37
     मशीन
    0.37
     CBE
    0.37
    POSITIVE LOGITS
    孝
    0.43
     espaço
    0.42
     avanzado
    0.38
    weł
    0.38
    বর্ধ
    0.37
    تقاوى
    0.37
     сельского
    0.37
    exitTool
    0.36
    erful
    0.36
     Jeho
    0.36
    Activations Density 0.000%

    No Known Activations