© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11619
    Prev
    Next
    INDEX
    Explanations

    mathematical publications, academic journals, and authors in the field, also paying attention to the structure and formatting typical to citations.

    oai_token-act-pair · gemini-2.0-flash

    mathematics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    GoogleApiClient
    -0.38
    вока
    -0.36
     performance
    -0.35
     Vella
    -0.35
    sim
    -0.35
     Struct
    -0.35
     
    -0.35
     مق
    -0.34
    нос
    -0.34
     اثر
    -0.34
    POSITIVE LOGITS
     proofs
    1.04
     mathematicians
    1.01
     proof
    0.96
     Proofs
    0.95
    proof
    0.92
     PROOF
    0.90
     Proof
    0.88
    Proof
    0.86
     algebra
    0.86
    rrggbb
    0.85
    Activations Density 18.701%

    No Known Activations