© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137125
    Prev
    Next
    INDEX
    Explanations

    German and English phrases

    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_12_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
    હેર
    0.56
     packing
    0.51
     grating
    0.51
    뿜
    0.51
    плат
    0.50
    ьте
    0.50
    fieldType
    0.50
     abiotic
    0.50
     हार्दिक
    0.49
     kính
    0.49
    POSITIVE LOGITS
    ک
    0.65
    k
    0.59
     اغلب
    0.57
     ότι
    0.56
    ik
    0.53
    imus
    0.53
    ya
    0.53
     episodios
    0.53
    ]
    0.52
     memahami
    0.52
    Activations Density 0.013%

    No Known Activations