© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10143
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols, equations, and notation

    oai_token-act-pair · gemini-2.0-flash

    patterns starting with 'su'

    np_token-act-pair-logits · gpt-4o-mini

    $

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    these
    -0.52
     dieselbe
    -0.52
    some
    -0.51
     dasselbe
    -0.50
    itself
    -0.50
    both
    -0.50
    それも
    -0.50
    Whereas
    -0.48
     keduanya
    -0.48
     tych
    -0.47
    POSITIVE LOGITS
     such
    0.97
     suche
    0.84
    uch
    0.81
     τέ
    0.79
     sue
    0.78
     ſuch
    0.77
     fuch
    0.76
     suc
    0.75
     euch
    0.75
     sucht
    0.70
    Activations Density 0.904%

    No Known Activations