© 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. 6287
    Prev
    Next
    INDEX
    Explanations

    mathematical equations, formulas, and statistical measures

    oai_token-act-pair · gemini-2.0-flash

    0

    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
    TypedDataSet
    -0.82
     <<<<<<<<<<<<<<
    -0.71
    bootstrapcdn
    -0.69
     initComponents
    -0.68
    ThroughAttribute
    -0.68
    queryInterface
    -0.66
    __*/
    -0.65
     '{@
    -0.64
    tagHelperRunner
    -0.63
    ähig
    -0.63
    POSITIVE LOGITS
    0
    0.57
    .
    0.56
     Agni
    0.46
    Portale
    0.45
    InteropServices
    0.45
     O
    0.41
    stagland
    0.40
    первых
    0.40
    gebnisse
    0.40
     epa
    0.40
    Activations Density 9.051%

    No Known Activations