© 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. 32368
    Prev
    Next
    INDEX
    Explanations

    website references

    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
    ຫຼ
    0.40
     toro
    0.40
     délic
    0.39
     N
    0.38
    sink
    0.37
     interchangeable
    0.37
     explorers
    0.37
     stel
    0.37
     déprimées
    0.36
     rena
    0.36
    POSITIVE LOGITS
     Sk
    0.48
     স্ক
    0.46
    Sk
    0.45
    蒯
    0.42
    Al
    0.40
     अल
    0.39
     বাক্য
    0.38
    CSS
    0.38
     Skinner
    0.38
     Al
    0.38
    Activations Density 0.000%

    No Known Activations