© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205738
    Prev
    Next
    INDEX
    Explanations

    water source or well

    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_37_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
     fountain
    1.16
     fountains
    1.12
     Fountain
    1.00
     fuente
    0.84
     fonte
    0.83
    泉
    0.81
     springs
    0.80
     font
    0.79
     fonts
    0.76
     Fontaine
    0.75
    POSITIVE LOGITS
     банк
    0.40
     Armee
    0.38
     బ్యాం
    0.37
     HUOBI
    0.37
     पारित
    0.37
    僄
    0.37
    chränk
    0.36
    Passed
    0.36
    ครัว
    0.36
    菌
    0.36
    Activations Density 0.010%

    No Known Activations