© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40115
    Prev
    Next
    INDEX
    Explanations

    refrigerator and refrigeration appliances

    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_11_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
    de
    0.63
     እነ
    0.58
    chim
    0.56
    2
    0.56
    1
    0.56
    ts
    0.54
    mails
    0.51
     ち
    0.50
    te
    0.49
    che
    0.49
    POSITIVE LOGITS
     refrigerators
    0.68
     supermarket
    0.64
     refrigeration
    0.64
     refrigerator
    0.63
     холоди
    0.60
     fridge
    0.57
     freezer
    0.55
    स्थ्य
    0.55
     appliance
    0.55
    ສາມາດ
    0.53
    Activations Density 0.029%

    No Known Activations