© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14549
    Prev
    Next
    INDEX
    Explanations

    text describing recipes or scientific studies involving shrimp

    oai_token-act-pair · gemini-2.0-flash

    shrimp

    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
    agrad
    -0.51
    üte
    -0.50
    üten
    -0.50
    uki
    -0.47
     kính
    -0.45
     operator
    -0.44
     rând
    -0.44
    istungen
    -0.43
    ย์
    -0.43
     kuş
    -0.43
    POSITIVE LOGITS
    ագրություններ
    0.91
    StructEnd
    0.75
    parsedMessage
    0.70
    Jeografia
    0.69
    таратура
    0.69
     transfieras
    0.64
     незавершена
    0.64
     Normdatei
    0.64
     wireType
    0.62
    EndContext
    0.61
    Activations Density 1.402%

    No Known Activations