© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115307
    Prev
    Next
    INDEX
    Explanations

    moon landing

    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_27_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
     phenols
    0.45
     phenol
    0.43
     normed
    0.41
     enzimas
    0.40
     нормально
    0.40
     normaal
    0.40
     enfermos
    0.39
    纾
    0.39
     renormalized
    0.39
     savk
    0.39
    POSITIVE LOGITS
    olan
    0.40
    orn
    0.38
     plus
    0.38
    phic
    0.38
     Code
    0.37
    accueil
    0.37
    lades
    0.36
    sch
    0.36
    hetic
    0.36
    ologically
    0.36
    Activations Density 0.003%

    No Known Activations