© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 304
    Prev
    Next
    INDEX
    Explanations

    the beginning of blocks of C# code

    oai_token-act-pair · gemini-2.0-flash

    HTML code

    np_max-act-logits · 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
    
    -0.87
    Portály
    -0.84
    Personensuche
    -0.81
    expandindo
    -0.81
    UserScript
    -0.80
     surla
    -0.78
    MLLoader
    -0.73
     Houſe
    -0.72
     houſe
    -0.72
    сылкі
    -0.69
    POSITIVE LOGITS
     Get
    0.50
    Get
    0.47
    u
    0.44
     
    0.38
    <em>
    0.37
    </td>
    0.37
     />
    0.36
    GetObject
    0.36
    </b>
    0.36
    </strong>
    0.36
    Activations Density 4.229%

    No Known Activations