© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 148966
    Prev
    Next
    INDEX
    Explanations

    Python dependencies

    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_23_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
    Ш
    0.49
    Drum
    0.43
     sepd
    0.42
    Ти
    0.41
    ತ್ವ
    0.40
    Viet
    0.39
    ął
    0.38
    umbuhan
    0.37
    繊
    0.37
     totalled
    0.37
    POSITIVE LOGITS
     Backbone
    0.37
     يتم
    0.37
     Carmel
    0.37
     Encore
    0.36
     Yous
    0.35
     watu
    0.35
     Actions
    0.35
     இரு
    0.35
     gimnas
    0.35
     enclave
    0.34
    Activations Density 0.001%

    No Known Activations