© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10122
    Prev
    Next
    INDEX
    Explanations

    instances of something replacing something else

    oai_token-act-pair · gemini-2.0-flash

    substitution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     replacing
    -1.39
     replaces
    -1.30
     replace
    -1.30
     replaced
    -1.30
     replacement
    -1.24
     Replace
    -1.20
     Replacing
    -1.20
    replacing
    -1.16
     Replacement
    -1.15
    replaced
    -1.13
    POSITIVE LOGITS
     tongue
    0.59
    Bibliograf
    0.56
    tongue
    0.53
    égorie
    0.48
    --){
    0.48
    impianto
    0.48
     ير
    0.47
     synthase
    0.47
     menn
    0.46
     starve
    0.46
    Activations Density 24.339%

    No Known Activations