© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 197855
    Prev
    Next
    INDEX
    Explanations

    computer science/AI papers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    Lav
    0.41
     Vend
    0.39
     Fins
    0.39
    Bruce
    0.38
    yfik
    0.38
    uspended
    0.38
    </thead>
    0.38
    Vend
    0.37
    उस
    0.37
    瀚
    0.37
    POSITIVE LOGITS
     ceb
    0.43
     McCle
    0.42
    澱
    0.40
     Keystone
    0.40
     گردد
    0.40
     keç
    0.39
     AppException
    0.38
    ྨ
    0.38
     Ke
    0.38
    collisions
    0.38
    Activations Density 0.000%

    No Known Activations