© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 254271
    Prev
    Next
    INDEX
    Explanations

    historical periods

    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_56_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
     Stream
    0.47
    лица
    0.41
    Stream
    0.40
    ssdk
    0.38
     Economies
    0.38
     Со
    0.37
    riffe
    0.37
    ज्ञान
    0.36
    ilia
    0.36
    蛆
    0.36
    POSITIVE LOGITS
     peak
    0.55
     role
    0.46
    role
    0.43
     simultaneous
    0.41
    Peak
    0.40
    peak
    0.40
     Peak
    0.39
     ongoing
    0.38
     peaks
    0.38
     نقش
    0.38
    Activations Density 0.010%

    No Known Activations