© 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. 6381
    Prev
    Next
    INDEX
    Explanations

    mentions of temperatures (in Celsius or Fahrenheit), percentages, and other scientific or technical parameters

    oai_token-act-pair · gemini-2.0-flash

    say "°"

    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
    interopRequire
    -0.60
    ftagPool
    -0.58
    Abitanti
    -0.58
    PreferredItem
    -0.52
    addContainerGap
    -0.52
    ensement
    -0.52
    UnknownFieldSet
    -0.52
    idopsis
    -0.52
     AssemblyTitle
    -0.51
     Meksiku
    -0.51
    POSITIVE LOGITS
     CAC
    1.12
    getC
    1.10
     CSC
    1.04
     getC
    1.03
    WC
    1.03
     WC
    1.02
     CMC
    0.99
     GC
    0.98
     JC
    0.98
    JC
    0.98
    Activations Density 8.370%

    No Known Activations