© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 64750
    Prev
    Next
    INDEX
    Explanations

    specific entities

    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_46_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
    푝
    0.40
     грун
    0.40
    ℤ
    0.39
    ichtung
    0.39
     зовніш
    0.38
    Mehr
    0.38
     পরিমাণ
    0.37
    έλ
    0.37
    
    0.37
    Seoul
    0.37
    POSITIVE LOGITS
     市
    0.39
     endregion
    0.39
     ४
    0.38
     Assert
    0.37
     Sixth
    0.36
     dek
    0.36
     Center
    0.35
     Brock
    0.35
     Seventh
    0.35
     Indigo
    0.35
    Activations Density 0.015%

    No Known Activations