© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5297
    Prev
    Next
    INDEX
    Explanations

    code snippets, programming or technical terminology

    oai_token-act-pair · gemini-2.0-flash

    Q

    np_max-act · gemini-2.0-flash

    Q

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     nahilalakip
    -1.13
     utafitiHapana
    -1.08
     surla
    -0.96
     виправивши
    -0.96
    脚注の使い方
    -0.94
    ंदीखरीदारी
    -0.85
    homonymie
    -0.84
    Попис
    -0.82
     ويكيميديا
    -0.80
    rungsseite
    -0.79
    POSITIVE LOGITS
    <eos>
    0.79
    TagMode
    0.68
    DllImport
    0.58
     more
    0.56
     who
    0.54
     be
    0.53
    ,
    0.52
     last
    0.51
     di
    0.51
     and
    0.50
    Activations Density 38.891%

    No Known Activations