© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 176388
    Prev
    Next
    INDEX
    Explanations

    thorn

    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_50_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
    ressa
    0.48
    etes
    0.42
     maestros
    0.39
     utu
    0.39
     معد
    0.37
     沈
    0.37
    滃
    0.36
    えば
    0.36
     لعب
    0.36
    }$&$
    0.36
    POSITIVE LOGITS
     Thorn
    1.68
     thorn
    1.58
     thorns
    1.35
    thorn
    1.34
     thor
    1.31
     THOR
    1.30
    Thor
    1.27
     Thor
    1.27
     Thorne
    1.27
     thorny
    1.24
    Activations Density 0.000%

    No Known Activations