© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59644
    Prev
    Next
    INDEX
    Explanations

    wildlife and property entities

    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_11_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
     signup
    0.37
    Signup
    0.36
     speculations
    0.36
     battalions
    0.35
    buri
    0.34
    React
    0.34
    ＿
    0.34
     profesionales
    0.34
     repercussions
    0.34
     reactionary
    0.34
    POSITIVE LOGITS
    dioxide
    0.42
    อื่นๆ
    0.40
     Waters
    0.38
     ô
    0.36
     Ganges
    0.35
     বৈশিষ্ট্য
    0.35
     Hughes
    0.35
     Nederlandse
    0.34
    clause
    0.33
     Europese
    0.33
    Activations Density 0.046%

    No Known Activations