© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3293
    Prev
    Next
    INDEX
    Explanations

    the word "diagram" and mathematical terms

    oai_token-act-pair · gemini-2.0-flash

    diagram

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     supérieurs
    -0.85
     supérieures
    -0.84
    RegressionTest
    -0.83
     connus
    -0.82
     fermés
    -0.78
     devenus
    -0.77
     préc
    -0.76
     sauvages
    -0.74
     prêtres
    -0.74
     démocr
    -0.73
    POSITIVE LOGITS
     ब्रेकडाउन
    0.71
     */;
    0.65
    ]++;
    0.63
    ſelves
    0.61
     }}$}
    0.60
     bezeichneter
    0.60
    BeginInit
    0.60
     anc
    0.59
    ".
    0.58
    BagConstraints
    0.58
    Activations Density 3.104%

    No Known Activations