© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 99618
    Prev
    Next
    INDEX
    Explanations

    hormonal, nuclear, breath, syringe, glucose, glycerol, lungs

    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_14_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
     sanguí
    0.29
     crux
    0.28
     minifyEnabled
    0.28
    决赛
    0.27
     creatine
    0.27
    ]))
    0.26
     myocardium
    0.26
     snugly
    0.26
    ]+
    0.26
     fate
    0.26
    POSITIVE LOGITS
    ário
    0.28
    urls
    0.27
    ared
    0.27
    앗
    0.26
    ents
    0.25
    ⊇
    0.25
    processes
    0.25
    aspect
    0.24
    effective
    0.24
    ets
    0.24
    Activations Density 0.031%

    No Known Activations