© 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. 12982
    Prev
    Next
    INDEX
    Explanations

    hexadecimal string addresses/identifiers

    oai_token-act-pair · gemini-2.0-flash

    Code/address context

    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
    li
    -0.36
    icks
    -0.35
    olta
    -0.35
     repute
    -0.33
    moja
    -0.31
    T
    -0.30
     campeón
    -0.30
    lore
    -0.30
     Kne
    -0.30
     i
    -0.30
    POSITIVE LOGITS
    kloped
    0.97
    MigrationBuilder
    0.91
    ReusableCell
    0.86
    tagHelperRunner
    0.86
     AspNetCore
    0.84
    ########.
    0.83
     виправивши
    0.83
    queryInterface
    0.81
    InitVars
    0.79
    DotNetBar
    0.79
    Activations Density 2.073%

    No Known Activations