© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137773
    Prev
    Next
    INDEX
    Explanations

    mystery shopper, food critic

    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_12_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
    Com
    0.59
    victim
    0.58
    com
    0.57
    발
    0.56
    1
    0.52
     than
    0.50
    ком
    0.50
    Serv
    0.49
    כ
    0.49
    Makefile
    0.49
    POSITIVE LOGITS
     escritores
    0.44
     процент
    0.43
     ঘন্টার
    0.43
     BufferedWriter
    0.42
     WERE
    0.42
     Schreiben
    0.41
     двигателя
    0.41
     měli
    0.41
     Nutzung
    0.40
    描写
    0.40
    Activations Density 0.002%

    No Known Activations