© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12716
    Prev
    Next
    INDEX
    Explanations

    tokens associated with the creation of something, whether it is tags or funds

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     created
    -2.77
     creation
    -2.61
     create
    -2.53
     creating
    -2.48
     Created
    -2.44
     Create
    -2.41
    created
    -2.39
     Creation
    -2.38
    Create
    -2.34
     Creating
    -2.34
    POSITIVE LOGITS
    ]")]
    0.56
    WireFormatLite
    0.55
     CallOverrides
    0.55
     Савезне
    0.51
    endphp
    0.50
     useAppContext
    0.50
    irited
    0.50
    getRuntime
    0.50
    ########.
    0.50
     Meksiku
    0.49
    Activations Density 2.237%

    No Known Activations