© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24417
    Prev
    Next
    INDEX
    Explanations

    psychologists or psychology

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     ކ
    0.39
    バラ
    0.39
    浱
    0.38
     taping
    0.37
    ilität
    0.37
    èse
    0.36
    ทอง
    0.36
     Crude
    0.35
     ['*.
    0.35
     Rhin
    0.35
    POSITIVE LOGITS
    Pi
    0.88
     pi
    0.87
    Erik
    0.80
     Erik
    0.78
     Pi
    0.71
    pi
    0.70
     Erickson
    0.65
     Bowl
    0.59
     Mas
    0.58
    Jean
    0.58
    Activations Density 0.126%

    No Known Activations