© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15821
    Prev
    Next
    INDEX
    Explanations

    code snippets and related features like include, define, import, and comments

    oai_token-act-pair · gemini-2.0-flash

    include

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     vPvB
    -0.52
    SpringRunner
    -0.50
    setViewportView
    -0.46
    zis
    -0.45
    /***/
    -0.45
    irmish
    -0.44
    ודם
    -0.44
    ep
    -0.44
    ursal
    -0.43
    lasm
    -0.43
    POSITIVE LOGITS
    IconModule
    0.77
    ftagPool
    0.75
    SequentialGroup
    0.73
    évaluateur
    0.72
    InSection
    0.69
    abestanden
    0.67
    IntoConstraints
    0.66
     >=",
    0.65
     Excell
    0.65
    rungsseite
    0.65
    Activations Density 5.115%

    No Known Activations