© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9711
    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_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
    objects
    0.38
    者
    0.38
     বাই
    0.38
    agents
    0.38
     answers
    0.38
     answering
    0.38
     agents
    0.37
     कर्
    0.37
    फ्रेंड
    0.36
    ctuaries
    0.35
    POSITIVE LOGITS
    忱
    0.44
    饶
    0.42
    瀑
    0.40
     provision
    0.38
     breat
    0.38
     Serializable
    0.38
     млад
    0.37
     brow
    0.36
    饒
    0.36
     سنة
    0.36
    Activations Density 0.021%

    No Known Activations