© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14890
    Prev
    Next
    INDEX
    Explanations

    code snippets and references, including javascript and URLs

    oai_token-act-pair · gemini-2.0-flash

    libs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     oprot
    -0.73
    ⓘ
    -0.69
    ografija
    -0.61
     transférez
    -0.60
    setVerticalGroup
    -0.59
    CodedInputStream
    -0.58
     صوتيه
    -0.57
    Портал
    -0.56
     دیکھیے
    -0.56
     picioare
    -0.56
    POSITIVE LOGITS
    Lähteet
    0.65
     snippetHide
    0.60
    HideFlags
    0.59
    CppMethod
    0.58
     שוליים
    0.55
     doInBackground
    0.52
    tableFuture
    0.50
    @[+][
    0.50
     NgModule
    0.50
     Italijani
    0.47
    Activations Density 2.598%

    No Known Activations