© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6864
    Prev
    Next
    INDEX
    Explanations

    phrases related to the creative process of media production and presentation

    oai_token-act-pair · gemini-2.0-flash

    programming terms or code components

    np_token-act-pair-logits · gpt-4o-mini

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     باخ
    -0.57
     gesteld
    -0.54
    Hochspringen
    -0.52
    ló
    -0.52
    eamento
    -0.49
    گر
    -0.47
    Iam
    -0.47
    formazione
    -0.46
    BDA
    -0.46
    기를
    -0.45
    POSITIVE LOGITS
    TintMode
    0.64
     يتيمه
    0.61
    ThroughAttribute
    0.60
    IonicModule
    0.59
    offsetof
    0.57
     initComponents
    0.57
    UnusedPrivate
    0.57
    createServer
    0.56
    queryInterface
    0.55
     Recre
    0.55
    Activations Density 1.203%

    No Known Activations