© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141856
    Prev
    Next
    INDEX
    Explanations

    Ignition software, SCADA, HMI, alarms

    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_12_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
    es
    0.69
    لې
    0.50
    Arte
    0.48
    S
    0.47
    Artifact
    0.45
    ItemStack
    0.44
    Type
    0.43
    菸
    0.43
    នៃការ
    0.42
    achelorette
    0.42
    POSITIVE LOGITS
     uniaxial
    0.52
    பால்
    0.48
     up
    0.48
    vou
    0.48
     headroom
    0.48
     hangs
    0.47
    ubert
    0.47
     reasons
    0.46
     ต้น
    0.46
     Gründe
    0.46
    Activations Density 0.004%

    No Known Activations