© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18216
    Prev
    Next
    INDEX
    Explanations

    to + VERB

    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_15_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
     filmm
    0.55
    😙
    0.50
    ส
    0.50
    的事情
    0.49
    💼
    0.49
    🎲
    0.48
    🔜
    0.47
     Abgerufen
    0.47
    骯
    0.47
     принад
    0.46
    POSITIVE LOGITS
    ar
    0.62
    AR
    0.56
     conveys
    0.50
    更多的
    0.47
     temper
    0.46
    as
    0.46
     ensures
    0.45
    ales
    0.44
    el
    0.44
     accelerates
    0.43
    Activations Density 0.068%

    No Known Activations