© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138498
    Prev
    Next
    INDEX
    Explanations

    **key signatures and musical tempo (BPM)**

    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_12_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
    ɪ
    0.63
    ê
    0.60
    </b>
    0.56
     amazing
    0.55
    </h2>
    0.54
    î
    0.54
     royal
    0.54
    ichi
    0.54
     NGO
    0.54
    </h1>
    0.53
    POSITIVE LOGITS
     ncol
    0.52
    蟎
    0.50
     stehen
    0.49
    പ്പെട്ട
    0.48
    Farland
    0.48
    糖尿
    0.47
     അല്ലെങ്കിൽ
    0.47
    嫨
    0.47
    uette
    0.46
     pharmaceut
    0.46
    Activations Density 0.051%

    No Known Activations