© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91914
    Prev
    Next
    INDEX
    Explanations

    allocating memory

    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_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ad
    1.13
    im
    0.95
    an
    0.94
    ill
    0.92
    (
    0.84
     has
    0.79
    ר
    0.76
    ob
    0.76
    ID
    0.76
    р
    0.74
    POSITIVE LOGITS
    ۳
    0.73
    の内容
    0.70
    ေး
    0.66
    ३
    0.58
    ές
    0.56
    ರಿಂದ
    0.56
    телем
    0.56
    τητας
    0.55
     malignancies
    0.55
    ၊
    0.55
    Activations Density 0.007%

    No Known Activations