© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2900
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and expressions, especially those containing fractions, exponents, and symbols like gamma, beta, delta, and psi.

    oai_token-act-pair · gemini-2.0-flash

    words with special or unusual characters

    np_token-act-pair-logits · gpt-4o-mini

    {

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    principalTable
    -0.64
    MigrationBuilder
    -0.60
    mybatisplus
    -0.57
     saites
    -0.56
    bootstrapcdn
    -0.56
     ostavi
    -0.54
    يدا
    -0.54
    writeField
    -0.54
     <=",
    -0.54
    uttavia
    -0.52
    POSITIVE LOGITS
     ſtate
    0.52
     juſ
    0.51
    getReal
    0.51
     sportif
    0.50
    1
    0.50
     Famille
    0.50
     deſ
    0.49
     poffible
    0.49
    ırken
    0.49
     onely
    0.49
    Activations Density 3.411%

    No Known Activations