© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 79951
    Prev
    Next
    INDEX
    Explanations

    Esc/Ped actions

    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_53_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
     t
    0.50
     т
    0.45
     T
    0.45
    GIF
    0.42
     ت
    0.40
     bor
    0.39
     اللا
    0.38
    ต
    0.38
    唓
    0.38
     අන
    0.37
    POSITIVE LOGITS
    esc
    0.45
     esc
    0.42
     Scrub
    0.38
    Esc
    0.38
    Ped
    0.36
    Push
    0.36
     esp
    0.36
     ped
    0.35
    ینو
    0.35
     Ped
    0.35
    Activations Density 0.054%

    No Known Activations