© 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. 15726
    Prev
    Next
    INDEX
    Explanations

    numbered lists

    oai_token-act-pair · gemini-2.0-flash

    technical or 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_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
    ↵↵
    -1.08
    ↵
    -0.89
    <eos>
    -0.78
    .
    -0.72
    ↵↵↵
    -0.71
    ,
    -0.71
     M
    -0.68
     O
    -0.66
     T
    -0.66
     A
    -0.65
    POSITIVE LOGITS
     crdi
    1.13
     Efq
    1.05
     photolibrary
    1.03
     greateſt
    0.97
     Majefty
    0.96
     Houſe
    0.94
     purpoſe
    0.92
     tfsi
    0.92
     moschino
    0.91
     ་་
    0.91
    Activations Density 4.515%

    No Known Activations