© 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. 3632
    Prev
    Next
    INDEX
    Explanations

    LaTeX code and mathematical forumlae

    oai_token-act-pair · gemini-2.0-flash

    math symbols

    np_max-act · gemini-2.0-flash
    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
     незавершена
    -1.05
    脚注の使い方
    -0.94
    
    -0.89
     resourceCulture
    -0.87
    tvguidetime
    -0.84
    httphttps
    -0.83
    igshid
    -0.82
    ThroughAttribute
    -0.82
    存于互联网档案馆
    -0.81
    afficheront
    -0.79
    POSITIVE LOGITS
    1
    0.60
    ↵↵
    0.58
    2
    0.55
    4
    0.53
    ↵
    0.52
    <eos>
    0.50
    3
    0.50
    9
    0.48
    The
    0.48
    طبي
    0.47
    Activations Density 4.885%

    No Known Activations