© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11754
    Prev
    Next
    INDEX
    Explanations

    Africa, Middle East, Asia, Europe

    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
    ność
    0.43
    0.40
     tetr
    0.39
     sax
    0.37
     Kxe
    0.36
    EditDialogOpen
    0.36
    0.36
    ---
    0.35
     portug
    0.35
     powst
    0.35
    POSITIVE LOGITS
    ži
    0.38
    핀
    0.38
     Ä
    0.37
     விரி
    0.36
    significant
    0.35
     significant
    0.34
     মিয়া
    0.34
    ุย
    0.34
     intu
    0.34
    quipe
    0.34
    Activations Density 0.040%

    No Known Activations