© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 148376
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    ?
    0.43
     costi
    0.43
     coût
    0.42
     стоимости
    0.42
     стоимость
    0.42
    costs
    0.40
    tem
    0.39
     variedade
    0.39
    cost
    0.39
    €.
    0.39
    POSITIVE LOGITS
     اظ
    0.35
    այն
    0.34
    لاك
    0.34
    ický
    0.33
    > </
    0.32
    اده
    0.32
    )$\
    0.32
    隂
    0.32
     laquelle
    0.32
    یاء
    0.32
    Activations Density 0.000%

    No Known Activations