© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6211
    Prev
    Next
    INDEX
    Explanations

    words associated with financial and economic instability and/or human suffering

    oai_token-act-pair · gemini-2.0-flash

    inflation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    .}~\
    -0.84
    ]='\
    -0.80
     ويكيپ
    -0.79
    .}(
    -0.78
     PeEn
    -0.77
    orative
    -0.77
    𓍊
    -0.77
     JpaRepository
    -0.76
    DeleteBehavior
    -0.75
    ICTOGRAM
    -0.74
    POSITIVE LOGITS
    <bos>
    2.47
    ↵↵
    0.93
    '
    0.85
    2
    0.71
    ↵
    0.70
    1
    0.69
    3
    0.67
    a
    0.67
    "
    0.60
    is
    0.59
    Activations Density 1.367%

    No Known Activations