© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11561
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming syntax

    oai_token-act-pair · gemini-2.0-flash

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ↵
    -0.75
    ↵↵
    -0.69
     A
    -0.68
    7
    -0.66
     "
    -0.65
     L
    -0.64
     '
    -0.64
     -
    -0.62
    8
    -0.60
     [
    -0.60
    POSITIVE LOGITS
     صوتيه
    1.14
     autorytatywna
    1.08
    Chham
    1.05
    principalColumn
    1.05
     Мексичка
    1.03
    сылкі
    1.00
     doInBackground
    1.00
     AssemblyCulture
    1.00
     InputDecoration
    0.99
    BufferException
    0.98
    Activations Density 0.624%

    No Known Activations