© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1234
    Prev
    Next
    INDEX
    Explanations

    LaTeX math symbols and syntax.

    oai_token-act-pair · gemini-2.0-flash

    Mathematics and machine learning

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ]='\
    -0.81
     '{@
    -0.79
    })->
    -0.71
    __);
    -0.71
     initComponents
    -0.70
    UAWEI
    -0.70
    AlterField
    -0.69
    SPJ
    -0.68
    Italien
    -0.67
    @",
    -0.67
    POSITIVE LOGITS
    left
    0.44
    right
    0.44
     pioggia
    0.41
     engraçadas
    0.38
     felizes
    0.38
     humaines
    0.35
    alpha
    0.34
     caduta
    0.34
     giustizia
    0.33
     complètes
    0.33
    Activations Density 1.440%

    No Known Activations