© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3800
    Prev
    Next
    INDEX
    Explanations

    LaTeX code and mathematical symbols

    oai_token-act-pair · gemini-2.0-flash

    underline

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     "..\..\..\
    -0.61
     "..\..\
    -0.55
    ->___
    -0.54
     SafeMath
    -0.53
    atguigu
    -0.52
     calitate
    -0.52
    Archie
    -0.51
    enetic
    -0.51
    Geor
    -0.51
     joaat
    -0.50
    POSITIVE LOGITS
    
    0.63
    SequentialGroup
    0.58
    PyExc
    0.57
     للمعارف
    0.53
    mybatisplus
    0.53
    Pozri
    0.50
    __":
    0.50
    DockStyle
    0.49
    تقاوى
    0.48
    Vezi
    0.47
    Activations Density 2.100%

    No Known Activations