© 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. 196036
    Prev
    Next
    INDEX
    Explanations

    marker names

    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
     M
    0.43
     Resolución
    0.40
    phyr
    0.38
     ಸ
    0.38
     MODKEY
    0.38
     ಲಾ
    0.37
    Lynn
    0.37
    Mâ
    0.37
     Lynn
    0.37
    痧
    0.37
    POSITIVE LOGITS
     Marke
    0.43
     mark
    0.41
     ,,
    0.39
     Mark
    0.39
     \,.
    0.38
     Fuse
    0.38
    ooka
    0.38
    त्रा
    0.38
     marker
    0.38
     মার্ক
    0.38
    Activations Density 0.007%

    No Known Activations