© 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. 195785
    Prev
    Next
    INDEX
    Explanations

    say installed

    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
    Held
    0.48
    held
    0.44
     held
    0.41
    Neur
    0.39
     purifying
    0.37
    賣
    0.37
     Held
    0.36
     برگزار
    0.36
    定め
    0.36
    standing
    0.36
    POSITIVE LOGITS
     Jeb
    0.38
    वों
    0.37
     ян
    0.36
     Jays
    0.35
     Arno
    0.34
     fif
    0.34
     сист
    0.34
     Jub
    0.34
    iería
    0.34
    顼
    0.34
    Activations Density 0.006%

    No Known Activations