© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10015
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially brand names, language/syntax markers, and calendar terms

    oai_token-act-pair · gemini-2.0-flash

    spring, events, fields

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     متعلقه
    -0.95
     AppCompatTheme
    -0.79
    setVerticalGroup
    -0.75
     ddelweddau
    -0.73
    enterOuterAlt
    -0.72
     Roskov
    -0.72
     TextAppearance
    -0.71
     referenties
    -0.71
     CURLOPT
    -0.69
     StatelessWidget
    -0.69
    POSITIVE LOGITS
    <bos>
    2.03
     the
    0.51
    ↵↵
    0.47
    '
    0.47
    s
    0.45
    G
    0.44
     in
    0.44
    ↵
    0.43
    t
    0.43
    B
    0.43
    Activations Density 2.695%

    No Known Activations