© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54004
    Prev
    Next
    INDEX
    Explanations

    doubled or increased

    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_30_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
     po
    0.32
    Notification
    0.30
    perm
    0.28
    appointment
    0.28
    👋
    0.28
     jamais
    0.27
     poit
    0.27
    NOTIFICATION
    0.27
    ↘
    0.27
    Appointment
    0.27
    POSITIVE LOGITS
    石头
    0.31
     Beide
    0.30
    rocytes
    0.30
     Kirchen
    0.28
     cvec
    0.28
    اونلو
    0.28
    বর্ধমান
    0.28
    ܫ
    0.28
     Wikipédia
    0.28
    മു
    0.28
    Activations Density 0.001%

    No Known Activations