© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12988
    Prev
    Next
    INDEX
    Explanations

    CD-ROMs or brick making

    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_40_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
     cape
    0.44
     capa
    0.38
     yun
    0.38
     Cape
    0.37
     Capp
    0.37
     xpath
    0.36
    Capp
    0.36
    陏
    0.36
     Sas
    0.36
     seme
    0.35
    POSITIVE LOGITS
     burned
    1.66
     burning
    1.56
     burn
    1.55
     burnt
    1.55
    燒
    1.53
    烧
    1.51
    burning
    1.49
    burned
    1.49
     burns
    1.48
    Burning
    1.46
    Activations Density 0.064%

    No Known Activations