© 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. 13386
    Prev
    Next
    INDEX
    Explanations

    code excerpts

    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
    <bos>
    -0.93
    tagHelperRunner
    -0.77
     esternos
    -0.52
     sum
    -0.49
     canlynol
    -0.48
    WebVitals
    -0.46
    webElement
    -0.46
    PropertyChanging
    -0.45
    Bril
    -0.44
    jupiter
    -0.44
    POSITIVE LOGITS
    #+#
    0.53
    ֱ
    0.52
     présidenti
    0.50
    nologies
    0.49
     chrétien
    0.48
    Citiți
    0.48
     africain
    0.47
    XmlAccessorType
    0.47
     libéral
    0.47
     graphiques
    0.47
    Activations Density 0.189%

    No Known Activations