© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9536
    Prev
    Next
    INDEX
    Explanations

    LaTeX math symbols, particularly those used in mathematical proofs

    oai_token-act-pair · gemini-2.0-flash

    mathbf

    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
     fé
    -0.45
     higher
    -0.43
     rising
    -0.40
     
    -0.38
    }}}$
    -0.38
     Den
    -0.38
     rise
    -0.38
    });*/
    -0.38
     assic
    -0.38
     الاص
    -0.38
    POSITIVE LOGITS
     nahilalakip
    0.96
    MethodManager
    0.89
    NewUrlParser
    0.83
    enumi
    0.82
    ScopeManager
    0.79
    oa̍t
    0.76
     дописавши
    0.73
    存于互联网档案馆
    0.72
     doInBackground
    0.69
     propOrder
    0.69
    Activations Density 1.307%

    No Known Activations