© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    4. 80825
    Prev
    Next
    INDEX
    Explanations

    even then

    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_29_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
     uploaded
    0.39
    둑
    0.38
     riv
    0.37
     hopefully
    0.36
     excepting
    0.36
     unlawfully
    0.36
     importantly
    0.36
     liver
    0.35
     BrowserModule
    0.35
    ponden
    0.35
    POSITIVE LOGITS
    手順
    0.42
    ógicos
    0.39
    ナ
    0.38
    ZW
    0.38
     απαι
    0.37
     বাস্তবায়
    0.36
    みて
    0.36
    Shaw
    0.36
    offerta
    0.35
    зь
    0.35
    Activations Density 0.005%

    No Known Activations