© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 6234
    Prev
    Next
    INDEX
    Explanations

    title = input

    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_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
    শায়
    0.38
    Keywords
    0.37
    葚
    0.37
    wpt
    0.36
    暌
    0.36
     middel
    0.35
    یسی
    0.35
    ंबू
    0.35
    dsl
    0.35
    뷰
    0.35
    POSITIVE LOGITS
     לת
    0.36
    subs
    0.34
     List
    0.33
    ΜΑ
    0.33
     লিস্ট
    0.33
    流畅
    0.33
     critic
    0.32
     lista
    0.32
    \,.
    0.32
    ListAdapter
    0.31
    Activations Density 0.001%

    No Known Activations