© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14540
    Prev
    Next
    INDEX
    Explanations

    words and phrases that are related to both textile arts and the arts broadly, particularly when modified by adjectives.

    oai_token-act-pair · gemini-2.0-flash

    art and craft

    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
     itſelf
    -0.70
     Reſ
    -0.65
     Anſ
    -0.62
     pleaſure
    -0.61
     ſche
    -0.60
    脚注の使い方
    -0.60
     ſta
    -0.60
    RenderAtEndOf
    -0.60
    طلحات
    -0.59
     ſte
    -0.58
    POSITIVE LOGITS
     art
    1.56
     craft
    1.28
     Art
    1.23
    Art
    1.13
    art
    1.04
     Craft
    0.97
    craft
    0.96
     trade
    0.96
     ART
    0.96
    Craft
    0.86
    Activations Density 2.493%

    No Known Activations