© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 121798
    Prev
    Next
    INDEX
    Explanations

    Thalina, Thulsa, Thomae

    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_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     threaten
    0.98
     threat
    0.89
     threatening
    0.86
    то
    0.82
     thread
    0.81
    ट
    0.80
    ﺧ
    0.79
    ید
    0.79
    та
    0.78
    ータ
    0.78
    POSITIVE LOGITS
    漼
    0.63
    kost
    0.62
    mány
    0.60
    chemic
    0.59
    kali
    0.58
    oja
    0.57
    éna
    0.57
    vale
    0.57
    context
    0.56
    寇
    0.56
    Activations Density 0.000%

    No Known Activations