© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12518
    Prev
    Next
    INDEX
    Explanations

    mathematical or code-like expressions, including greek letters, symbols, and a mix of letters and numbers

    oai_token-act-pair · gemini-2.0-flash

    math formulas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    GEBURTSDATUM
    -0.98
    ########.
    -0.96
    SharedDtor
    -0.95
    expandindo
    -0.94
     ExecuteAsync
    -0.94
     doubtnut
    -0.93
     Roskov
    -0.89
    锈钢
    -0.89
    IVEREF
    -0.87
    rrggbb
    -0.83
    POSITIVE LOGITS
     
    0.67
     \
    0.51
     <
    0.49
     ,
    0.49
     —
    0.48
     .
    0.47
     third
    0.47
     ]
    0.46
     $\
    0.46
     of
    0.46
    Activations Density 1.370%

    No Known Activations