© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216685
    Prev
    Next
    INDEX
    Explanations

    else or :

    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_31_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
     ending
    0.35
     性
    0.31
     coming
    0.30
     nest
    0.30
     machines
    0.30
     Fold
    0.30
     delinquent
    0.29
    iniz
    0.29
     Destiny
    0.29
    ঞ্ছ
    0.29
    POSITIVE LOGITS
    ட்க
    0.35
     duplo
    0.35
    水分
    0.34
    উদাহরণ
    0.33
     connective
    0.33
    豫
    0.32
    Para
    0.32
    Wasser
    0.32
    ählte
    0.31
    Easter
    0.31
    Activations Density 0.002%

    No Known Activations