© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 239195
    Prev
    Next
    INDEX
    Explanations

    mongodb://localhost:27017

    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_25_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
    ঁচ
    0.44
    দীর
    0.43
     sò
    0.42
     sfera
    0.40
     числі
    0.40
    secs
    0.40
     eel
    0.39
    蟶
    0.38
     bathe
    0.38
    ensional
    0.38
    POSITIVE LOGITS
    介绍
    0.42
    </html>
    0.36
    指示
    0.36
     (-)
    0.35
     задержа
    0.35
    错过
    0.35
    Null
    0.35
    </h2>
    0.34
     NOTE
    0.34
     '$(
    0.34
    Activations Density 0.001%

    No Known Activations