© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 68299
    Prev
    Next
    INDEX
    Explanations

    adverbs

    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_51_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
    तरी
    0.47
    楽しめる
    0.43
     می‌توانید
    0.40
    存在する
    0.39
     უნდა
    0.39
     they
    0.38
     இருக்கிறது
    0.38
     '+'
    0.38
    始まった
    0.38
     refusing
    0.37
    POSITIVE LOGITS
    aterally
    0.52
    atically
    0.50
    astically
    0.49
    elessly
    0.48
    fully
    0.48
    ously
    0.47
    actively
    0.47
    operatively
    0.47
    ologically
    0.46
    itionally
    0.45
    Activations Density 0.298%

    No Known Activations