© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6671
    Prev
    Next
    INDEX
    Explanations

    words or phrases in the beginning or end of a sentence, paragraph, or document related to supporting information, documentation, or instructions

    oai_token-act-pair · gemini-2.0-flash

    words related to information

    np_token-act-pair-logits · gpt-4o-mini

    information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    IntoConstraints
    -0.78
    DockStyle
    -0.69
    InjectAttribute
    -0.60
    expandindo
    -0.57
    makeConstraints
    -0.56
     Signalez
    -0.52
     TimeUnit
    -0.47
     canst
    -0.47
    newtheorem
    -0.47
    下载附件
    -0.46
    POSITIVE LOGITS
     information
    2.20
     info
    1.99
     Information
    1.88
    information
    1.88
    Information
    1.74
     informations
    1.74
     INFORMATION
    1.73
     información
    1.66
     Info
    1.66
     details
    1.66
    Activations Density 3.841%

    No Known Activations