© 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. 35464
    Prev
    Next
    INDEX
    Explanations

    many followed by plural nouns

    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
    I
    0.58
     I
    0.56
    ো
    0.54
    د
    0.52
    ل
    0.52
    ن
    0.52
    ン
    0.50
    ه
    0.49
    ਰ
    0.48
    㚼
    0.48
    POSITIVE LOGITS
     MGM
    0.68
    ни
    0.66
    0
    0.60
    4
    0.60
     aggiungere
    0.58
     oferecer
    0.57
     Wenger
    0.56
     считаю
    0.56
     доступны
    0.55
    🈺
    0.55
    Activations Density 0.004%

    No Known Activations