© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 808
    Prev
    Next
    INDEX
    Explanations

    comfortable, curiosity, excitement, hunger

    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_39_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
     متخصص
    0.40
     partnership
    0.39
     Zusammenarbeit
    0.38
    連携
    0.38
    쪽
    0.38
     cooperation
    0.38
     Edwin
    0.37
    鎵
    0.37
    参与
    0.37
     getServer
    0.36
    POSITIVE LOGITS
     Comfortable
    0.47
     discomfort
    0.45
     comfortable
    0.43
     നടപ
    0.40
    comfortable
    0.40
     curiosity
    0.40
     excitement
    0.40
     hunger
    0.40
    Comfort
    0.39
    舒服
    0.39
    Activations Density 0.096%

    No Known Activations