© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4439
    Prev
    Next
    INDEX
    Explanations

    code that uses numbers or double data

    oai_token-act-pair · gemini-2.0-flash

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    endforeach
    -0.50
    HtmlAttribute
    -0.48
     мәкал
    -0.47
     endforeach
    -0.46
     BoxDecoration
    -0.46
     Gleaner
    -0.44
     crossings
    -0.44
    TabView
    -0.44
    XmlSchema
    -0.43
     princí
    -0.43
    POSITIVE LOGITS
    存于互联网档案馆
    0.62
    IContainer
    0.59
    detectChanges
    0.58
     autorytatywna
    0.58
    rrggbb
    0.53
    TagHelper
    0.53
    íses
    0.52
     تانيه
    0.52
    imageshack
    0.50
     payé
    0.50
    Activations Density 2.679%

    No Known Activations