© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10257
    Prev
    Next
    INDEX
    Explanations

    words and phrases that involve comparing two things.

    oai_token-act-pair · gemini-2.0-flash

    diverse names and terms

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

    comparative words

    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
    MigrationBuilder
    -0.54
    B
    -0.47
     vœux
    -0.46
     latine
    -0.42
    space
    -0.42
    PA
    -0.41
    %)$
    -0.41
     justiça
    -0.41
    C
    -0.41
    дешь
    -0.40
    POSITIVE LOGITS
    Portale
    0.83
    IndentedString
    0.69
     незавершена
    0.68
     سكانية
    0.68
    FormTagHelper
    0.67
    istoitu
    0.66
     then
    0.65
    SBATCH
    0.63
     kaarangay
    0.62
     оригіналу
    0.62
    Activations Density 10.981%

    No Known Activations