© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7587
    Prev
    Next
    INDEX
    Explanations

    technical writing about computer architecture

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    AddTagHelper
    -1.07
     AssemblyCompany
    -0.71
    rrggbb
    -0.65
    LabelTagHelper
    -0.64
    ритори
    -0.55
    ArrowToggle
    -0.54
    numerusform
    -0.53
     Signalez
    -0.53
    errHandler
    -0.52
    principalColumn
    -0.52
    POSITIVE LOGITS
     Vo
    0.54
     noDo
    0.53
     >::
    0.52
    Vo
    0.52
    ArgsConstructor
    0.50
    tvguidetime
    0.49
     estu
    0.48
    reportWebVitals
    0.47
     Dimensional
    0.47
     jsPsych
    0.46
    Activations Density 10.392%

    No Known Activations