© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 15526
    Prev
    Next
    INDEX
    Explanations

    code blocks

    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_34_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
     স্বে
    0.39
    wsdl
    0.37
     Last
    0.36
     正規
    0.36
    ]].
    0.36
    \</
    0.36
     hello
    0.35
    ėti
    0.35
    </ul>
    0.34
     Hello
    0.34
    POSITIVE LOGITS
    انو
    0.39
     atmosfer
    0.39
    Hu
    0.39
    émor
    0.39
    Lavender
    0.38
    聾
    0.38
     സംഭ
    0.37
    זי
    0.36
    hu
    0.36
     vigorously
    0.36
    Activations Density 0.002%

    No Known Activations