© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5706
    Prev
    Next
    INDEX
    Explanations

    monetary values and percentages

    oai_token-act-pair · gemini-2.0-flash

    Numbers, statistics, or money

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     AssemblyProduct
    -1.00
     Efq
    -0.92
     الحره
    -0.90
     myſelf
    -0.84
     jScrollPane
    -0.84
     nakalista
    -0.84
     Monfieur
    -0.82
    EndInit
    -0.78
    قایناق‌لار
    -0.76
    +#+#
    -0.75
    POSITIVE LOGITS
    SourceChecksum
    0.53
     Ru
    0.47
    XmlSchema
    0.47
    cro
    0.46
     getC
    0.46
    unik
    0.45
    BU
    0.44
     Man
    0.44
     X
    0.43
    Cri
    0.43
    Activations Density 2.482%

    No Known Activations