© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 236016
    Prev
    Next
    INDEX
    Explanations

    configuration parameters

    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_25_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
    ုတ်
    0.37
     rubbed
    0.36
     ওষুধের
    0.35
     epoxy
    0.34
    ,"
    0.34
    chem
    0.33
     (
    0.33
     chemically
    0.33
     superimposed
    0.33
     reag
    0.32
    POSITIVE LOGITS
     élevées
    0.38
    ิค
    0.37
     ಹಲ
    0.37
    ิท
    0.36
    雜
    0.36
     పలు
    0.36
     Исто
    0.35
    truncate
    0.34
     Или
    0.34
    त्रा
    0.34
    Activations Density 0.002%

    No Known Activations