© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120106
    Prev
    Next
    INDEX
    Explanations

    shape and size descriptors

    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_27_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
     belts
    0.38
    pyridazin
    0.38
     উদ্বাস্তুদের
    0.37
    ಿತಿ
    0.37
     weaves
    0.37
     reacted
    0.37
    竝
    0.37
    織
    0.36
     took
    0.35
     alt
    0.35
    POSITIVE LOGITS
    证
    0.39
    Diamond
    0.38
    نوع
    0.38
     szé
    0.37
    Time
    0.37
    refined
    0.37
    diamond
    0.36
    Fully
    0.36
    ideal
    0.34
    Eloquent
    0.34
    Activations Density 0.009%

    No Known Activations