© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 194367
    Prev
    Next
    INDEX
    Explanations

    natural refrigerant

    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_15_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
    ك
    0.63
    Handlers
    0.51
     ምን
    0.51
     ስለዚህ
    0.49
     چو
    0.49
    辂
    0.49
     نیک
    0.49
     መድ
    0.49
    聸
    0.48
    ди
    0.48
    POSITIVE LOGITS
     minimally
    0.47
     family
    0.47
     rare
    0.47
     developed
    0.47
     section
    0.47
     $\
    0.45
     accumulated
    0.45
     weekend
    0.44
     decorating
    0.44
     plants
    0.43
    Activations Density 0.000%

    No Known Activations