© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8783
    Prev
    Next
    INDEX
    Explanations

    sections of legal, scientific, or official documents, including numbers and identifiers

    oai_token-act-pair · gemini-2.0-flash

    terms related to numbers and decrees

    np_token-act-pair-logits · gpt-4o-mini

    number

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    通販
    -0.50
    ngths
    -0.48
    antaranya
    -0.48
     HomeComponent
    -0.45
     spreken
    -0.44
     emplois
    -0.44
    ⅘
    -0.43
     Polskiego
    -0.42
     للمعارف
    -0.42
     AssemblyProduct
    -0.42
    POSITIVE LOGITS
     number
    1.74
     no
    1.58
     No
    1.55
    number
    1.43
     Number
    1.39
    No
    1.37
     num
    1.34
     NUMBER
    1.31
     numbers
    1.28
     número
    1.27
    Activations Density 2.159%

    No Known Activations