© 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. 9835
    Prev
    Next
    INDEX
    Explanations

    financial information, especially related to taxes, cents, and numeric values

    oai_token-act-pair · gemini-2.0-flash

    cents

    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
    OleDb
    -0.48
    MessageDigest
    -0.46
     vectorielles
    -0.46
     safely
    -0.45
    (&:
    -0.42
    ervo
    -0.42
     kedai
    -0.41
    orsch
    -0.40
     flatter
    -0.40
    Porter
    -0.40
    POSITIVE LOGITS
    TagHelpers
    0.78
     contextLoads
    0.74
    новниш
    0.64
    LabelTagHelper
    0.63
    DebuggerNonUser
    0.62
    DeleteBehavior
    0.61
    Anlage
    0.60
    tagHelper
    0.58
     FontWeight
    0.58
    MLLoader
    0.57
    Activations Density 1.236%

    No Known Activations