© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170222
    Prev
    Next
    INDEX
    Explanations

    model

    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_56_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
    做出
    0.38
    formations
    0.38
     مزاج
    0.38
    拂
    0.38
     победи
    0.35
    చిత
    0.35
    㶲
    0.35
     constructions
    0.35
     Capri
    0.35
    실
    0.34
    POSITIVE LOGITS
     tends
    1.38
     tended
    1.24
     tending
    1.09
     tend
    0.99
     Tend
    0.97
    Tend
    0.97
    Help
    0.94
     tende
    0.94
     help
    0.93
     Help
    0.92
    Activations Density 0.016%

    No Known Activations