© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 659
    Prev
    Next
    INDEX
    Explanations

    file includes, code syntax and math symbols

    oai_token-act-pair · gemini-2.0-flash

    library/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
     Wade
    -0.65
     Kante
    -0.63
     Rollins
    -0.63
     }_{
    -0.63
    Gilla
    -0.62
     Indexes
    -0.62
    āti
    -0.61
    Wade
    -0.60
     Sixth
    -0.60
     Alli
    -0.60
    POSITIVE LOGITS
     Caruso
    0.69
    SourceChecksum
    0.65
     Hartmann
    0.62
     Whitley
    0.61
     Freeman
    0.60
     Cornel
    0.59
    drv
    0.59
     Damon
    0.58
     Merritt
    0.58
    Portail
    0.58
    Activations Density 4.206%

    No Known Activations