© 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. 12450
    Prev
    Next
    INDEX
    Explanations

    phrases expressing positivity or high praise

    oai_token-act-pair · gemini-2.0-flash

    positive comparison

    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
    artig
    -0.63
    ppets
    -0.53
    ranton
    -0.48
    hpur
    -0.48
     ThemeData
    -0.48
     betekenis
    -0.46
     &___
    -0.46
    ul
    -0.46
    yanka
    -0.44
    protoimpl
    -0.43
    POSITIVE LOGITS
    IsContent
    0.63
    archiviato
    0.56
     CURIAM
    0.56
    tał
    0.54
    InjectAttribute
    0.54
    ngdoc
    0.53
    pexpr
    0.52
    BASEPATH
    0.51
    stdc
    0.49
    ientôt
    0.49
    Activations Density 1.468%

    No Known Activations