© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4229
    Prev
    Next
    INDEX
    Explanations

    terms and journals related to theoretical physics and mathematics

    oai_token-act-pair · gemini-2.0-flash

    Phys

    np_max-act · gemini-2.0-flash

    academic fields

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    AutoScaleMode
    -0.92
     متعلقه
    -0.91
     betweenstory
    -0.89
     ArrayAdapter
    -0.88
    moiselle
    -0.85
     ſy
    -0.85
    BibitemShut
    -0.83
     FetchType
    -0.83
     Diſ
    -0.82
     Theſe
    -0.82
    POSITIVE LOGITS
    <bos>
    1.13
    ’
    0.88
    ↵↵
    0.85
    '
    0.85
    ↵
    0.66
      
    0.64
    The
    0.62
    \
    0.60
    ‘
    0.60
     
    0.59
    Activations Density 4.344%

    No Known Activations