© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6822
    Prev
    Next
    INDEX
    Explanations

    control/bail/form/incite/seize

    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
    Not in Any Lists

    No Comments

    Negative Logits
    📢
    0.26
     visualization
    0.26
     Visualize
    0.25
     visualisation
    0.25
     idealism
    0.25
     hybridization
    0.25
    ㅁ
    0.25
     cerim
    0.23
     ಅತ್ಯ
    0.23
    añ
    0.23
    POSITIVE LOGITS
     एर
    0.25
    responding
    0.24
     substant
    0.23
     christ
    0.23
     lob
    0.22
    <unused47>
    0.22
    seek
    0.22
     tout
    0.22
    ustan
    0.22
     clandest
    0.22
    Activations Density 0.189%

    No Known Activations