© 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. 2992
    Prev
    Next
    INDEX
    Explanations

    LaTeX code, in particular math mode equations

    oai_token-act-pair · gemini-2.0-flash

    Code/scientific papers

    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
    F
    -0.43
    S
    -0.43
    T
    -0.42
     sensaciones
    -0.42
     möj
    -0.42
     célèbres
    -0.42
     razões
    -0.42
     leçons
    -0.40
     alrededores
    -0.39
    B
    -0.39
    POSITIVE LOGITS
     Elas
    0.79
    }$​
    0.76
     Lorraine
    0.75
     
    0.74
     Chol
    0.74
     Concer
    0.74
     Ashford
    0.73
    ](#
    0.73
     NTB
    0.73
     Kek
    0.72
    Activations Density 1.456%

    No Known Activations