© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3913
    Prev
    Next
    INDEX
    Explanations

    words and phrases that are somewhat technical in nature and occur in research articles

    oai_token-act-pair · gemini-2.0-flash

    Experiments and trade-offs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ]--;
    -0.63
    audiovisuel
    -0.57
    ClientSize
    -0.56
    Identyfik
    -0.54
     intptr
    -0.52
    InputBorder
    -0.51
     Preferencias
    -0.50
    Према
    -0.50
    ]++;
    -0.48
     numerus
    -0.48
    POSITIVE LOGITS
    <bos>
    1.79
    ########.
    0.69
     ويكيپيديا
    0.65
    #
    0.56
     treats
    0.50
     chi̍t
    0.48
    etcode
    0.48
     surla
    0.47
     itſelf
    0.47
    tamment
    0.46
    Activations Density 24.672%

    No Known Activations