© 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. 252528
    Prev
    Next
    INDEX
    Explanations

    virtual environments

    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
    綎
    0.39
    仴
    0.37
    盒子
    0.36
     soln
    0.36
     HEL
    0.35
     मॅ
    0.35
     detn
    0.35
     permeable
    0.35
    න්ද
    0.35
    揊
    0.34
    POSITIVE LOGITS
     an
    0.54
    env
    0.45
    ધા
    0.41
     diplom
    0.41
    chir
    0.39
    grown
    0.38
    built
    0.38
    coprote
    0.38
    ाय
    0.36
     জীবন
    0.36
    Activations Density 0.001%

    No Known Activations