© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 198941
    Prev
    Next
    INDEX
    Explanations

    best use

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     любить
    0.47
     সত্যি
    0.46
     verdad
    0.45
    जान
    0.44
    赐
    0.44
     grab
    0.43
    truth
    0.42
    ชอบ
    0.42
    grab
    0.41
    loving
    0.41
    POSITIVE LOGITS
     best
    0.49
     terbaik
    0.46
    ੰ
    0.42
     use
    0.42
     iterations
    0.40
     usamos
    0.40
     using
    0.40
     safest
    0.39
     menggunakan
    0.38
     comp
    0.37
    Activations Density 0.003%

    No Known Activations