© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2173
    Prev
    Next
    INDEX
    Explanations

    configuration management

    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_39_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
     Calls
    0.42
    Calls
    0.41
    माज
    0.41
    ⚭
    0.38
     szt
    0.38
     aproape
    0.38
     রম
    0.37
     pups
    0.37
    調
    0.37
    hews
    0.36
    POSITIVE LOGITS
     replicating
    0.41
     servic
    0.37
     Replication
    0.37
     osmosis
    0.37
     overloading
    0.36
     Sentinel
    0.36
     Développement
    0.36
     Replica
    0.35
     ஆயிரம்
    0.35
     സേ
    0.35
    Activations Density 0.016%

    No Known Activations