© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 29528
    Prev
    Next
    INDEX
    Explanations

    Option 3:

    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_40_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
     too
    0.42
    太
    0.36
     presentations
    0.36
     ot
    0.35
     اچھا
    0.35
     ऑपरेशन
    0.35
     bt
    0.34
    態
    0.34
     thảo
    0.34
     TOO
    0.34
    POSITIVE LOGITS
     changer
    0.39
     cambiado
    0.39
     cambiato
    0.39
    вр
    0.38
     postérieur
    0.38
     changé
    0.37
     solicitud
    0.37
     cambió
    0.37
     changed
    0.36
    เปลี่ยน
    0.35
    Activations Density 0.018%

    No Known Activations