© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5984
    Prev
    Next
    INDEX
    Explanations

    alphanumeric identifiers separated by dashes

    oai_token-act-pair · gemini-2.0-flash

    code diffs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     D
    -0.52
     d
    -0.50
    D
    -0.46
     i
    -0.41
    rådet
    -0.33
    hå
    -0.32
     italiane
    -0.32
     Д
    -0.32
     olvid
    -0.32
     x
    -0.31
    POSITIVE LOGITS
    TagMode
    1.16
     AssemblyCulture
    1.07
     ―――――
    1.02
    InitVars
    1.01
    脚注の使い方
    1.00
     esternos
    0.99
     ་་
    0.99
     препратки
    0.98
     GenerationType
    0.96
     itſelf
    0.94
    Activations Density 1.156%

    No Known Activations