© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14049
    Prev
    Next
    INDEX
    Explanations

    syrup or shopper complaints

    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_15_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
    AC
    0.54
    BE
    0.54
    qPCR
    0.54
    ↵
    0.52
    GC
    0.51
    C
    0.50
    Type
    0.50
    DNA
    0.50
    approx
    0.49
    Cat
    0.49
    POSITIVE LOGITS
     później
    0.57
     Vysok
    0.57
     Adu
    0.55
    ွမ်း
    0.54
     Decree
    0.52
     schützen
    0.52
     Subsequent
    0.52
     liczba
    0.52
    Ổ
    0.52
     Độ
    0.50
    Activations Density 0.000%

    No Known Activations