© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 214097
    Prev
    Next
    INDEX
    Explanations

    say "thor"

    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_47_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
    [{\
    0.42
     quarta
    0.38
    જા
    0.37
     uč
    0.36
    ufieurs
    0.36
     মনো
    0.35
    Abb
    0.35
     گوئی
    0.35
     Adin
    0.35
    旱
    0.34
    POSITIVE LOGITS
     Thor
    2.66
    Thor
    2.64
     thor
    2.31
    thor
    2.17
     thoracic
    2.17
     THOR
    2.17
     thorium
    1.76
     thorac
    1.71
     thorax
    1.70
     thoracique
    1.69
    Activations Density 0.001%

    No Known Activations