© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9973
    Prev
    Next
    INDEX
    Explanations

    code snippets, file paths, and tutorial instructions

    oai_token-act-pair · gemini-2.0-flash

    software installation

    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
    Personendaten
    -0.82
    ########.
    -0.81
    utnik
    -0.69
     betweenstory
    -0.68
    :✨
    -0.67
    SourceChecksum
    -0.65
    ?')
    -0.65
    intios
    -0.64
    Spoljašnje
    -0.63
    GraphicsUnit
    -0.63
    POSITIVE LOGITS
    postcss
    0.42
     amp
    0.42
     awk
    0.41
     合
    0.41
    appspot
    0.40
    av
    0.40
    olt
    0.40
     rat
    0.40
    typename
    0.39
    antd
    0.39
    Activations Density 5.279%

    No Known Activations