© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 3157
    Prev
    Next
    INDEX
    Explanations

    Siemens

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
     blister
    0.41
    洧
    0.39
    Mard
    0.39
    嶆
    0.39
     काउंसिल
    0.39
     nM
    0.38
    apeti
    0.37
     Ayl
    0.37
    邑
    0.37
     hetero
    0.36
    POSITIVE LOGITS
    Siem
    1.98
     Siemens
    1.98
     Siem
    1.38
     si
    1.07
    si
    1.07
     Si
    1.02
     SI
    1.02
     سي
    0.98
     Сі
    0.97
    Si
    0.96
    Activations Density 0.009%

    No Known Activations