© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5169
    Prev
    Next
    INDEX
    Explanations

    phrases indicating something is important or plays a role

    oai_token-act-pair · gemini-2.0-flash

    essential roles in various contexts

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

    Importance

    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
     very
    -0.82
    very
    -0.75
     createSprite
    -0.69
     VERY
    -0.68
     considerable
    -0.67
     muy
    -0.66
     big
    -0.66
    Very
    -0.66
     significant
    -0.65
     très
    -0.65
    POSITIVE LOGITS
     싶
    0.66
    phazard
    0.60
     autorytatywna
    0.56
    出版年
    0.56
    KommentareTeilen
    0.55
    PYX
    0.54
    MethodManager
    0.52
     سكانية
    0.52
    setGeometry
    0.51
    躇
    0.51
    Activations Density 3.885%

    No Known Activations