© 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-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14245
    Prev
    Next
    INDEX
    Explanations

    code, specifically go code

    oai_token-act-pair · gemini-2.0-flash

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.71
     Akademi
    -0.68
    MessageOf
    -0.67
     acad
    -0.66
     acadé
    -0.66
     Akade
    -0.64
    Academics
    -0.63
    akade
    -0.61
     akad
    -0.61
     aca
    -0.60
    POSITIVE LOGITS
     InputDecoration
    0.75
     vectorielles
    0.57
     Réponses
    0.55
    Enllaces
    0.52
     Verenigde
    0.52
     convertView
    0.52
    PreExecute
    0.52
    centralwidget
    0.51
     consultato
    0.51
    তথ্যসূত্র
    0.51
    Activations Density 2.765%

    No Known Activations