© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15176
    Prev
    Next
    INDEX
    Explanations

    code snippets and descriptions of neural network architectures

    oai_token-act-pair · gemini-2.0-flash

    code

    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
     a
    -0.76
     k
    -0.68
     c
    -0.68
     d
    -0.67
     v
    -0.65
     protoimpl
    -0.64
     qu
    -0.62
     und
    -0.61
     "
    -0.61
     s
    -0.61
    POSITIVE LOGITS
    ſelf
    1.53
    ſelves
    1.48
     Efq
    1.45
     itſelf
    1.42
     Majefty
    1.38
     Monfieur
    1.38
     Houſe
    1.35
     iſt
    1.34
     myſelf
    1.32
     houſe
    1.31
    Activations Density 1.575%

    No Known Activations