© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12668
    Prev
    Next
    INDEX
    Explanations

    code snippets involving pointers and memory management

    oai_token-act-pair · gemini-2.0-flash

    underscores and parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    นิ
    -0.50
     name
    -0.46
    ESH
    -0.45
     direct
    -0.45
    مم
    -0.44
    Flu
    -0.44
    gul
    -0.44
     earth
    -0.43
     Flu
    -0.43
    elseif
    -0.43
    POSITIVE LOGITS
    ArrowToggle
    0.68
    writeFieldEnd
    0.66
    PreferredItem
    0.60
     iprot
    0.60
    tanleria
    0.57
     ComVisible
    0.55
     jScrollPane
    0.55
     pamamagitan
    0.54
    WhereInput
    0.54
     Baillargeon
    0.53
    Activations Density 0.500%

    No Known Activations