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. 5781
    Prev
    Next
    INDEX
    Explanations

    phrases describing physical and mental (in)abilities

    oai_token-act-pair · gemini-2.0-flash

    terms related to medical documentation

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

    cognitive or physical difficulty

    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
     Lives
    -0.51
    ulturen
    -0.51
     plugs
    -0.48
    oush
    -0.47
    Spoljašnje
    -0.46
    afficheront
    -0.45
     sitesinde
    -0.45
    jsii
    -0.44
     PHPUnit
    -0.44
    hances
    -0.43
    POSITIVE LOGITS
    IntoConstraints
    0.75
     Wiktionnaire
    0.68
    MessageOf
    0.66
     صوتيه
    0.64
     الرياضيه
    0.63
    GraphicsUnit
    0.61
    RegressionTest
    0.59
    ollectionView
    0.57
    __':
    0.57
    __":
    0.57
    Activations Density 1.085%

    No Known Activations