© 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
    2. Gemma-3-27B-IT
    3. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 11774
    Prev
    Next
    INDEX
    Explanations

    cephalosporin antibiotics

    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_13_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
     Use
    0.20
    汞
    0.20
     Treat
    0.20
    Treat
    0.20
     TREAT
    0.19
     টাকায়
    0.18
    Table
    0.18
    Use
    0.17
     G
    0.17
     Table
    0.17
    POSITIVE LOGITS
    ol
    0.18
     रास्ता
    0.17
     בפ
    0.17
     راستہ
    0.17
    ademia
    0.16
    lement
    0.16
    ành
    0.16
    ശേഷ
    0.16
    atars
    0.16
    pons
    0.16
    Activations Density 0.005%

    No Known Activations