© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15652
    Prev
    Next
    INDEX
    Explanations

    symbols related to math, errors, and locations

    oai_token-act-pair · gemini-2.0-flash

    mathematical symbols and formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    MigrationBuilder
    -0.96
    jsonwebtoken
    -0.82
    findpost
    -0.79
     EconPapers
    -0.77
    tonode
    -0.76
     invokingState
    -0.71
    rawDesc
    -0.70
    oredCriteria
    -0.68
    ChildIndex
    -0.63
    DJANGO
    -0.62
    POSITIVE LOGITS
     اطراف
    0.52
     flanking
    0.51
     surrounding
    0.50
     retor
    0.50
    四周
    0.49
     surrounds
    0.49
    mpä
    0.47
     surround
    0.47
    respectively
    0.46
     connexes
    0.46
    Activations Density 1.336%

    No Known Activations