© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 211664
    Prev
    Next
    INDEX
    Explanations

    Trappist, Benedictine, Zen, intrinsic value

    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_19_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
    ROIT
    0.50
    RO
    0.43
     RE
    0.41
    ５
    0.41
     RA
    0.41
     RET
    0.39
     Rosen
    0.39
     Eighty
    0.39
     Rich
    0.37
    Rich
    0.37
    POSITIVE LOGITS
     énon
    0.52
    implantation
    0.50
     puisi
    0.49
     mosques
    0.47
    椏
    0.46
     idempot
    0.46
     humanist
    0.45
     biocompat
    0.45
     deont
    0.45
    EtOH
    0.44
    Activations Density 0.000%

    No Known Activations