© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 167130
    Prev
    Next
    INDEX
    Explanations

    wait, skip, and common

    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_31_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
    气
    0.46
     Pap
    0.39
    リューション
    0.38
     ozbil
    0.38
     Senator
    0.36
    Articles
    0.36
     Reserva
    0.36
    ඡ
    0.36
    Senator
    0.36
     सैयद
    0.36
    POSITIVE LOGITS
    fahren
    0.48
    skip
    0.42
     sustit
    0.40
    ركه
    0.38
    wait
    0.38
     fach
    0.38
     spikes
    0.37
    waiting
    0.37
    ekwondo
    0.37
     waited
    0.37
    Activations Density 0.000%

    No Known Activations