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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 9630
    Prev
    Next
    INDEX
    Explanations

    code snippets with comments and government regulations

    oai_token-act-pair · gemini-2.0-flash

    stub

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     MainAxisSize
    -0.53
    Слайд
    -0.48
     FontWeight
    -0.48
    anguera
    -0.48
     pylab
    -0.46
    uhnya
    -0.46
     själ
    -0.46
    UREAU
    -0.45
     okuyayım
    -0.45
    Highest
    -0.44
    POSITIVE LOGITS
    <bos>
    1.80
    SourceChecksum
    0.68
    ’
    0.59
    /$',
    0.57
     برانيه
    0.56
    туга
    0.56
    URLException
    0.54
    "])){
    0.54
     Infórmanos
    0.54
    '
    0.54
    Activations Density 0.180%

    No Known Activations