© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12653
    Prev
    Next
    INDEX
    Explanations

    gas and explosions

    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_13_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
     peru
    0.54
     Unidos
    0.52
     exploited
    0.48
     clas
    0.48
     esti
    0.47
    ន្ត
    0.46
     Algarve
    0.46
     k
    0.45
     admitted
    0.45
     mutu
    0.45
    POSITIVE LOGITS
    remove
    0.60
    ems
    0.56
    9
    0.55
    err
    0.54
    www
    0.54
    ony
    0.52
    resistant
    0.52
    race
    0.52
    Cam
    0.51
    Gee
    0.51
    Activations Density 0.028%

    No Known Activations