© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59033
    Prev
    Next
    INDEX
    Explanations

    usual suspects

    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
    タ
    0.79
    پ
    0.77
    م
    0.72
    the
    0.69
    ン
    0.64
    お
    0.64
    フ
    0.63
    あ
    0.63
    주
    0.59
    인
    0.59
    POSITIVE LOGITS
     получи
    0.63
     siquiera
    0.63
     realmente
    0.60
    )
    0.58
    ида
    0.56
     cr
    0.55
     MSE
    0.54
     l
    0.54
     ডিগ্রি
    0.54
     você
    0.54
    Activations Density 0.005%

    No Known Activations