© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4877
    Prev
    Next
    INDEX
    Explanations

    ventilation and cooling fans

    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_39_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
     फ्ला
    0.40
     کپ
    0.38
    RESSION
    0.36
    გუფი
    0.36
     Wilhel
    0.36
    sonaro
    0.35
    紂
    0.34
    䀓
    0.34
     Szt
    0.34
     bandes
    0.33
    POSITIVE LOGITS
     ventilation
    1.69
     fan
    1.63
     ventil
    1.59
     fans
    1.57
     Ventilation
    1.57
     венти
    1.55
     Fans
    1.47
     vent
    1.41
     vents
    1.40
     Ventil
    1.38
    Activations Density 0.097%

    No Known Activations