© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7890
    Prev
    Next
    INDEX
    Explanations

    technical content from patents and engineering documents

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    featureID
    -0.67
    tuan
    -0.52
     unas
    -0.51
    InitStruct
    -0.51
     afin
    -0.50
     via
    -0.50
    geon
    -0.50
    ได้
    -0.49
    ToMany
    -0.49
    źnie
    -0.49
    POSITIVE LOGITS
     ſhould
    0.64
     muſt
    0.60
     Monfieur
    0.59
     Efq
    0.58
     Económica
    0.56
    Ờ
    0.53
     ontvang
    0.53
     sbag
    0.51
     ſhall
    0.51
     could
    0.49
    Activations Density 7.152%

    No Known Activations