© 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. 10498
    Prev
    Next
    INDEX
    Explanations

    scientific or technical texts, especially that describe experiments (or the parameters of experiments) that use some sort of radiation

    oai_token-act-pair · gemini-2.0-flash

    High/low

    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
    PROTOBUF
    -0.53
    vivi
    -0.47
     traitement
    -0.47
    کہ
    -0.46
    ionView
    -0.46
    Rcpp
    -0.46
     Vikipedi
    -0.46
     FirebaseAuth
    -0.45
     BaseController
    -0.45
     utafitiHapana
    -0.44
    POSITIVE LOGITS
     Efq
    0.75
     myſelf
    0.74
    exitRule
    0.73
     resourceCulture
    0.69
    WriteBarrier
    0.68
     يتيمه
    0.66
    كويكب
    0.65
     kasarigan
    0.64
     defaultstate
    0.64
     juſ
    0.62
    Activations Density 2.778%

    No Known Activations