© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14620
    Prev
    Next
    INDEX
    Explanations

    statistical data

    oai_token-act-pair · gemini-2.0-flash

    Numbers

    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
     InputDecoration
    -0.73
    SequentialGroup
    -0.65
    dafx
    -0.59
    Twice
    -0.58
     Twice
    -0.56
     насељу
    -0.56
    ListItemIcon
    -0.55
     Lordships
    -0.52
    ագրություններ
    -0.52
    حيان
    -0.52
    POSITIVE LOGITS
     three
    2.38
     four
    2.36
     five
    2.20
    three
    2.05
     six
    1.98
    four
    1.97
     trois
    1.93
     seven
    1.91
    five
    1.84
     quatre
    1.83
    Activations Density 5.574%

    No Known Activations