Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5747
    Prev
    Next
    INDEX
    Explanations

    words related to the modification and use of starch in food

    oai_token-act-pair · gemini-2.0-flash

    cooking-related terms

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

    food science

    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
    +#+#
    -0.70
    Демографія
    -0.66
     autorytatywna
    -0.65
     صوتيه
    -0.65
     يتيمه
    -0.64
     المعيارى
    -0.64
     présidenti
    -0.63
    KommentareTeilen
    -0.63
    ագրություններ
    -0.60
    ValueStyle
    -0.60
    POSITIVE LOGITS
     cooking
    0.51
     oil
    0.48
    理
    0.47
    omonas
    0.47
    }^{(
    0.47
    setAccessible
    0.45
     color
    0.44
     sensory
    0.44
     fires
    0.43
    dge
    0.43
    Activations Density 2.264%

    No Known Activations