© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13142
    Prev
    Next
    INDEX
    Explanations

    LaTeX code snippets and related terms.

    oai_token-act-pair · gemini-2.0-flash

    LaTeX code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Efq
    -1.78
     myſelf
    -1.74
     itſelf
    -1.66
    ſelf
    -1.66
     Monfieur
    -1.65
     Majefty
    -1.64
     Theſe
    -1.63
     ſeveral
    -1.63
     themſelves
    -1.59
    ſelves
    -1.58
    POSITIVE LOGITS
    ↵↵
    0.96
    <eos>
    0.79
     
    0.73
    .
    0.66
     The
    0.66
     (
    0.60
     E
    0.60
     A
    0.59
     -
    0.58
    (
    0.58
    Activations Density 14.621%

    No Known Activations