© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18730
    Prev
    Next
    INDEX
    Explanations

    dryness balanced lighter bright complex

    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_40_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
     heats
    0.41
     heat
    0.40
    odge
    0.39
     oxi
    0.38
     chaleur
    0.38
    뿍
    0.38
    taste
    0.38
    heat
    0.38
     тепло
    0.37
     वनडे
    0.37
    POSITIVE LOGITS
     dry
    0.96
     Dry
    0.93
    Dry
    0.91
    dry
    0.89
     drier
    0.79
     dryness
    0.78
    干
    0.76
     DRY
    0.74
     сухо
    0.70
     dryer
    0.70
    Activations Density 0.052%

    No Known Activations