© 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. 40304
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions indicating "for" or "by", leading to explanations or specifications

    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
    ే
    0.38
    ت
    0.35
     NEET
    0.34
    ات
    0.33
    мо
    0.32
    一
    0.32
     OneDrive
    0.32
    в
    0.32
    ة
    0.31
     Roblox
    0.31
    POSITIVE LOGITS
    ų
    0.34
     mewah
    0.34
     putih
    0.32
     ہیں
    0.30
     زنان
    0.29
     mancanza
    0.29
    use
    0.29
     aromas
    0.29
    hetam
    0.28
     سرمایہ
    0.28
    Activations Density 0.043%

    No Known Activations