© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 19130
    Prev
    Next
    INDEX
    Explanations

    thoughts and out of head

    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_34_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
     অপরা
    0.41
     童
    0.39
    Increasing
    0.38
     yanında
    0.38
    沟
    0.38
    োপা
    0.37
     annivers
    0.36
     Catalyst
    0.35
    缘
    0.35
    يرا
    0.35
    POSITIVE LOGITS
     brain
    0.76
     head
    0.75
    腦
    0.74
    頭
    0.73
     Head
    0.72
    脑袋
    0.70
    大脑
    0.69
    头
    0.69
     Kopf
    0.68
    Head
    0.67
    Activations Density 0.008%

    No Known Activations