© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 63826
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_41_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
     abond
    0.40
     chữ
    0.37
    тым
    0.37
     BES
    0.37
    朲
    0.37
     буква
    0.36
    Diagnostics
    0.36
    ধ্ব
    0.36
     newMovie
    0.36
    衷
    0.36
    POSITIVE LOGITS
     agent
    2.13
     agents
    1.99
    agent
    1.84
     Agent
    1.79
     Agents
    1.79
    Agent
    1.78
     аген
    1.75
     agentes
    1.73
     agente
    1.73
    agents
    1.70
    Activations Density 0.000%

    No Known Activations