© 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. 13708
    Prev
    Next
    INDEX
    Explanations

    phrases that describe the way things appear

    oai_token-act-pair · gemini-2.0-flash

    plausible content and variations

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

    Opinion/assessment using "seem/sound"

    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
    '],
    -0.52
    VStack
    -0.51
    "];
    -0.48
    )}</
    -0.48
    FormTagHelper
    -0.48
    "](
    -0.48
    Припев
    -0.47
    "],
    -0.47
    ")]
    -0.47
    ']
    -0.46
    POSITIVE LOGITS
    脚注の使い方
    0.68
     مرئيه
    0.60
     BeautifulSoup
    0.58
    :+:
    0.57
     Krakowie
    0.55
    aryen
    0.54
    quiao
    0.54
     plausible
    0.54
    ériques
    0.51
    TagMode
    0.51
    Activations Density 1.568%

    No Known Activations