© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 1457
    Prev
    Next
    INDEX
    Explanations

    Grand

    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_44_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
     Chud
    0.42
     Franck
    0.39
     துன்ப
    0.39
     Francois
    0.39
    闶
    0.38
    لن
    0.38
    过渡
    0.38
    减轻
    0.38
    quota
    0.37
     Saver
    0.37
    POSITIVE LOGITS
     gran
    1.52
     Gran
    1.39
    Gran
    1.39
    gran
    1.38
     granular
    1.29
     granules
    1.29
     granulation
    1.27
     granule
    1.27
     GRAN
    1.26
     granul
    1.25
    Activations Density 0.004%

    No Known Activations