© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13412
    Prev
    Next
    INDEX
    Explanations

    pizza and delivery

    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_40_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
     Amsterdam
    0.58
    Amsterdam
    0.53
    🌃
    0.48
     downtown
    0.47
     Downtown
    0.46
     Glasgow
    0.45
    Downtown
    0.45
     NYC
    0.44
    ⛪
    0.42
     Gotham
    0.42
    POSITIVE LOGITS
    柞
    0.41
     Microwave
    0.41
     apr
    0.36
    émi
    0.36
    ochlorite
    0.36
     OVA
    0.36
    RootManager
    0.36
    柳
    0.36
     minuto
    0.35
    DWARF
    0.35
    Activations Density 0.030%

    No Known Activations