© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 165798
    Prev
    Next
    INDEX
    Explanations

    melt or melting

    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_34_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
     Martinez
    0.41
     Hydrogen
    0.40
    飧
    0.40
     hydrated
    0.39
    氫
    0.39
    Revenue
    0.38
     hydrogen
    0.38
    单元
    0.38
     Erectile
    0.38
     dailySales
    0.38
    POSITIVE LOGITS
     melted
    1.12
     melt
    1.05
     melts
    1.05
     melting
    1.01
    melt
    1.00
    melting
    0.96
     molten
    0.93
    熔
    0.93
     Melting
    0.89
     Melt
    0.85
    Activations Density 0.006%

    No Known Activations