© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11790
    Prev
    Next
    INDEX
    Explanations

    parts of a configuration dialog

    oai_token-act-pair · gemini-2.0-flash

    layer

    np_max-act · gemini-2.0-flash
    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
    ubereitung
    -0.65
    inaldi
    -0.58
    cagon
    -0.58
    poche
    -0.56
    Diagnostics
    -0.54
    AttributeSet
    -0.54
     rowspan
    -0.53
     Instrument
    -0.53
     little
    -0.53
    HtmlAttribute
    -0.52
    POSITIVE LOGITS
    <bos>
    1.22
     autorytatywna
    0.79
    Personensuche
    0.76
     cherchés
    0.68
     Мексичка
    0.66
     lenker
    0.64
     GenerationType
    0.63
    లాలు
    0.61
     समीक्षाएं
    0.60
     Савезне
    0.59
    Activations Density 1.418%

    No Known Activations