© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 83957
    Prev
    Next
    INDEX
    Explanations

    feeling safe and comfortable

    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_29_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
     यामुळे
    0.38
    anfaatkan
    0.38
    candidate
    0.37
    RY
    0.37
    Successful
    0.36
    horse
    0.36
    ]/(
    0.36
    ]];
    0.35
    ghost
    0.35
    Blocking
    0.35
    POSITIVE LOGITS
     encounters
    0.50
     throughout
    0.46
     import
    0.42
     toxins
    0.40
     cycles
    0.39
     encountering
    0.39
     encounter
    0.38
     problèmes
    0.38
     problemat
    0.38
    tego
    0.38
    Activations Density 0.006%

    No Known Activations