© 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. 12201
    Prev
    Next
    INDEX
    Explanations

    code comments and programming keywords.

    oai_token-act-pair · gemini-2.0-flash

    code

    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
     CanadaChoose
    -0.73
     MaterialApp
    -0.71
    jspb
    -0.68
     Koto
    -0.68
     utafitiHapana
    -0.67
     onCancelled
    -0.67
    abetes
    -0.66
     unknownFields
    -0.65
    AppCompatTheme
    -0.61
    djangoproject
    -0.61
    POSITIVE LOGITS
     dem
    0.53
    AnchorTagHelper
    0.47
     chàng
    0.40
     通販
    0.39
     Mr
    0.37
    ::::::::
    0.35
    UNITIES
    0.35
    crombie
    0.35
    tiously
    0.35
     din
    0.34
    Activations Density 0.445%

    No Known Activations