© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12298
    Prev
    Next
    INDEX
    Explanations

    numbers, percentages, and units of measure appearing in scientific texts.

    oai_token-act-pair · gemini-2.0-flash

    technical/scientific text

    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
    am
    -0.74
     Diſ
    -0.72
     itſelf
    -0.71
    m
    -0.68
     pleaſure
    -0.67
     myſelf
    -0.67
     ſever
    -0.66
     themſelves
    -0.65
     fevere
    -0.64
    ca
    -0.62
    POSITIVE LOGITS
    ratulations
    0.72
    sustainability
    0.70
    sustainable
    0.66
    #%%
    0.66
    minimalist
    0.65
    esterol
    0.64
    }*/
    0.63
    QUENCE
    0.63
    unisex
    0.63
    ecutive
    0.63
    Activations Density 4.591%

    No Known Activations