© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 177492
    Prev
    Next
    INDEX
    Explanations

    firebase, speech, crowds

    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_29_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
     comparability
    0.41
     maxSize
    0.40
     coherence
    0.37
    ेटर
    0.37
     comparable
    0.37
     unto
    0.37
     communion
    0.37
     parseInt
    0.36
    ܙ
    0.36
     execut
    0.36
    POSITIVE LOGITS
    Indoor
    0.45
    Cantidad
    0.43
    Wallpaper
    0.43
    Installed
    0.40
     Indoor
    0.39
    Outdoor
    0.39
    userdata
    0.39
    Dopo
    0.39
    indoor
    0.38
    Olá
    0.38
    Activations Density 0.000%

    No Known Activations