© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 136869
    Prev
    Next
    INDEX
    Explanations

    aroma

    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
     taste
    0.60
     tast
    0.59
     tastes
    0.58
     palpable
    0.55
    味
    0.55
     Taste
    0.53
     вкус
    0.53
     вку
    0.53
    맛
    0.53
     delicious
    0.50
    POSITIVE LOGITS
    promise
    0.46
     promise
    0.46
    Promises
    0.45
     promises
    0.42
     overw
    0.41
    Promise
    0.41
     обеща
    0.40
     Promises
    0.40
    Hyd
    0.39
    Drinking
    0.39
    Activations Density 0.002%

    No Known Activations