© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15614
    Prev
    Next
    INDEX
    Explanations

    alphanumeric IDs for products

    oai_token-act-pair · gemini-2.0-flash

    model numbers and specs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    migrationBuilder
    -1.09
     leaſt
    -0.86
    IndentedString
    -0.83
     useAppContext
    -0.82
    tagHelperRunner
    -0.82
    RegistryLite
    -0.82
     tartalomajánló
    -0.81
     تانيه
    -0.79
    #+#
    -0.78
     bezeichneter
    -0.76
    POSITIVE LOGITS
     i
    0.53
    saraba
    0.52
    i
    0.51
    II
    0.50
    合
    0.49
    T
    0.49
    cu
    0.47
    tab
    0.47
     ta
    0.47
    ра
    0.46
    Activations Density 2.183%

    No Known Activations