© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 140997
    Prev
    Next
    INDEX
    Explanations

    wheat

    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
    营
    0.42
     ksi
    0.38
    Conv
    0.37
    Gr
    0.37
    resents
    0.37
     Aze
    0.37
    onnements
    0.37
    圃
    0.37
     cocinar
    0.36
    пени
    0.36
    POSITIVE LOGITS
    ક્
    0.42
     Arsen
    0.40
    ridine
    0.40
     Call
    0.38
     BUILDING
    0.37
     Ar
    0.37
     ar
    0.36
     Really
    0.36
     అక్క
    0.36
     call
    0.35
    Activations Density 0.001%

    No Known Activations