© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12051
    Prev
    Next
    INDEX
    Explanations

    snippets of code, chemical formulas and mathematical equations

    oai_token-act-pair · gemini-2.0-flash

    Code/technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    PhysRevLett
    -0.54
    hlar
    -0.53
    CppMethod
    -0.52
    nonatomic
    -0.52
     AssemblyCulture
    -0.50
     lá
    -0.48
    Skocz
    -0.47
    PhysRev
    -0.47
    let
    -0.46
    getColumnIndex
    -0.45
    POSITIVE LOGITS
    InSection
    0.69
    onViewCreated
    0.68
     myſelf
    0.66
     Eſ
    0.63
     himſelf
    0.61
     purpoſe
    0.58
     poffible
    0.57
    abadi
    0.57
     Diſ
    0.57
     presidents
    0.54
    Activations Density 2.469%

    No Known Activations