© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57304
    Prev
    Next
    INDEX
    Explanations

    syrup and sugar alternatives

    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_11_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
    0.46
    지
    0.45
     प्रचंड
    0.43
    locals
    0.42
    ită
    0.41
    itters
    0.41
    Loc
    0.40
    Ireland
    0.40
    CALL
    0.39
    Italy
    0.39
    POSITIVE LOGITS
    minent
    0.50
     Maple
    0.49
     путем
    0.46
     Boon
    0.45
     Aj
    0.45
     Bunker
    0.44
    ẏ
    0.43
     Lyn
    0.43
     Pontiac
    0.43
     Pittsburg
    0.43
    Activations Density 0.024%

    No Known Activations