© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13896
    Prev
    Next
    INDEX
    Explanations

    zhè, zhège, zhè yī (this)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_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
     성능
    0.57
    years
    0.57
    ⁺
    0.54
    ter
    0.54
    Patrick
    0.52
    ओएस
    0.52
     потери
    0.52
     गे
    0.51
    OSE
    0.50
    Princess
    0.50
    POSITIVE LOGITS
     alveolar
    0.55
     unusual
    0.54
     vacío
    0.54
     A
    0.54
     appuy
    0.53
    ástico
    0.52
     chiar
    0.52
     reserva
    0.51
     όχι
    0.51
    א
    0.51
    Activations Density 0.010%

    No Known Activations