© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5675
    Prev
    Next
    INDEX
    Explanations

    code and code documentation

    oai_token-act-pair · gemini-2.0-flash

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    <bos>
    -0.93
    Description
    -0.52
    ItemLayout
    -0.50
    ElementException
    -0.50
     Description
    -0.49
    Beschreibung
    -0.47
     estimés
    -0.47
     GeV
    -0.47
     description
    -0.46
    UserScript
    -0.46
    POSITIVE LOGITS
    GEBURTS
    0.86
    __*/
    0.75
    bootstrapcdn
    0.66
    BindView
    0.64
     pinulongan
    0.63
     >=",
    0.63
    getMenuInflater
    0.60
    Portail
    0.60
    getSupport
    0.60
    marginVertical
    0.59
    Activations Density 1.445%

    No Known Activations