© 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. 154868
    Prev
    Next
    INDEX
    Explanations

    say 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
    滃
    0.46
    ressa
    0.40
    僖
    0.39
    িব
    0.37
    汔
    0.37
     لعب
    0.36
    }$&$
    0.36
     SKY
    0.36
    暨
    0.36
    ாட்ட
    0.36
    POSITIVE LOGITS
     Thorn
    1.85
     thorn
    1.71
     thorns
    1.52
     thor
    1.47
     THOR
    1.46
    thorn
    1.42
     Thorne
    1.41
     Thor
    1.38
    Thor
    1.37
     thorny
    1.35
    Activations Density 0.001%

    No Known Activations