© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1724
    Prev
    Next
    INDEX
    Explanations

    Hegemony, Hegelian, Scheveningen, Hepatic

    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_39_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
     cheats
    0.51
     ヘ
    0.50
     хе
    0.46
     Heap
    0.46
     heap
    0.46
     cheating
    0.44
     Che
    0.44
     hé
    0.44
     Hé
    0.44
    𒆜
    0.44
    POSITIVE LOGITS
     মামলার
    0.37
    ohr
    0.36
    ertas
    0.36
    ecc
    0.36
    azim
    0.36
    みる
    0.34
    igenza
    0.34
    uent
    0.34
    xh
    0.34
    ohm
    0.34
    Activations Density 0.021%

    No Known Activations