© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175196
    Prev
    Next
    INDEX
    Explanations

    be followed by past participle

    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_20_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
     помочь
    0.38
    ্বেও
    0.33
     ගැනීමට
    0.32
     ช่วย
    0.31
     revenir
    0.31
     permitem
    0.31
     તમારે
    0.30
     來
    0.30
    ³.
    0.30
     permiten
    0.30
    POSITIVE LOGITS
     horror
    0.30
     infancy
    0.29
     the
    0.28
    殚
    0.28
     production
    0.27
    发现
    0.27
     frequented
    0.27
    N
    0.27
     afflicted
    0.27
     וח
    0.27
    Activations Density 0.005%

    No Known Activations