© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11447
    Prev
    Next
    INDEX
    Explanations

    hyphens and other ascii characters used to format numbers, dates, measurements, or ranges, in scientific text

    oai_token-act-pair · gemini-2.0-flash

    Delimiters/connectors

    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
     CascadeType
    -0.64
     sẻ
    -0.54
     JAXBElement
    -0.54
     EconPapers
    -0.51
    ne
    -0.51
    makeConstraints
    -0.49
    AndroidJUnit
    -0.48
     ApiException
    -0.47
     Cytometry
    -0.47
    pesar
    -0.47
    POSITIVE LOGITS
     Shakspeare
    0.66
    MigrationBuilder
    0.58
     Samaria
    0.56
    al
    0.54
    errHandler
    0.54
    ally
    0.53
    AL
    0.53
    ScopeManager
    0.53
     Cæsar
    0.52
    Personensuche
    0.52
    Activations Density 13.749%

    No Known Activations