© 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. 249599
    Prev
    Next
    INDEX
    Explanations

    model output formatting

    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
    L
    1.30
    Л
    1.30
     Л
    1.30
     Λ
    1.17
    Ｌ
    1.17
     ล
    1.16
     ல
    1.02
     ਲ
    1.01
    Λ
    1.00
     L
    0.98
    POSITIVE LOGITS
     Vec
    0.34
    ſon
    0.33
     FURN
    0.32
     furnish
    0.32
     IList
    0.31
     வாய
    0.31
     চু
    0.31
    чених
    0.31
    ക്ഷ
    0.30
    సూ
    0.30
    Activations Density 0.013%

    No Known Activations