© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176701
    Prev
    Next
    INDEX
    Explanations

    depression, depressed, depressive

    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_20_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
     injectors
    0.47
     সুইচ
    0.46
    යක්
    0.45
     Mechanics
    0.44
     Again
    0.43
    ímica
    0.42
     transmis
    0.42
    ữ
    0.42
     mechanics
    0.42
    ilise
    0.42
    POSITIVE LOGITS
    祝
    0.46
    HZ
    0.45
    TRO
    0.44
     リュ
    0.42
    HANG
    0.42
    Servlet
    0.42
    HAL
    0.42
    Trou
    0.42
     racconto
    0.42
    SYN
    0.40
    Activations Density 0.004%

    No Known Activations