© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 204724
    Prev
    Next
    INDEX
    Explanations

    dry

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     tender
    0.69
    tender
    0.64
    嫩
    0.59
     Tender
    0.58
     tenderness
    0.57
     Cris
    0.52
     tendered
    0.51
     tenders
    0.49
     CRIS
    0.48
    Cris
    0.48
    POSITIVE LOGITS
     dry
    0.94
     Dry
    0.84
    Dry
    0.80
    dry
    0.75
    干
    0.74
     干
    0.69
     сухо
    0.64
     cold
    0.64
    cold
    0.60
    幹
    0.60
    Activations Density 0.086%

    No Known Activations