© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5377
    Prev
    Next
    INDEX
    Explanations

    You can find more information

    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_40_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
     Dil
    0.42
    ttes
    0.39
     sati
    0.39
    可
    0.38
     yes
    0.38
     ett
    0.38
     Meny
    0.37
     SAT
    0.36
    GS
    0.35
    否
    0.35
    POSITIVE LOGITS
     idempot
    0.38
    زش
    0.38
     beat
    0.36
    Beat
    0.36
    Should
    0.36
     রওনা
    0.35
     cumpleaños
    0.35
    柒章
    0.35
     fond
    0.34
    Bast
    0.33
    Activations Density 0.048%

    No Known Activations