© 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. 13109
    Prev
    Next
    INDEX
    Explanations

    sentences which frequently include the words "we", "that", "not", and words related to killing/disease/death.

    oai_token-act-pair · gemini-2.0-flash

    Quotes and extracted snippets

    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
    paper
    -0.42
    msubsup
    -0.39
    treeview
    -0.39
    :
    -0.39
     i
    -0.38
     Congress
    -0.38
     spelled
    -0.37
     Figure
    -0.36
    s
    -0.36
    an
    -0.36
    POSITIVE LOGITS
    RectangleBorder
    1.05
    expandindo
    0.85
     oprot
    0.82
     beginnetje
    0.79
    rungsseite
    0.75
    adpleegd
    0.74
    IndentedString
    0.74
    oredCriteria
    0.72
     Савезне
    0.72
    parsedMessage
    0.70
    Activations Density 3.067%

    No Known Activations