Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 10298
    Prev
    Next
    INDEX
    Explanations

    text indicating the beginning of a note, edit or answer

    oai_token-act-pair · gemini-2.0-flash

    note edit

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     nahilalakip
    -0.64
    ']],
    -0.58
    WithIOException
    -0.54
     AssemblyCulture
    -0.53
    arXiv
    -0.52
    )|^{
    -0.52
    原始内容存档于
    -0.51
    \{\\
    -0.50
    。"
    -0.49
    +");
    -0.49
    POSITIVE LOGITS
    :
    1.44
    :
    1.11
     :
    1.02
     :
    0.93
    :
    
    0.92
    ®:
    0.87
    :—
    0.80
    }:
    0.79
    :\
    0.78
    ]:
    0.77
    Activations Density 1.945%

    No Known Activations