© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12847
    Prev
    Next
    INDEX
    Explanations

    sentences with some reporting verb and the word 'that'

    oai_token-act-pair · gemini-2.0-flash

    news reports

    np_max-act · gemini-2.0-flash

    verbs

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     CreateTagHelper
    -0.74
    kloped
    -0.57
     unknownFields
    -0.56
    httphttps
    -0.56
    ChildScrollView
    -0.55
     geslacht
    -0.54
    FormTagHelper
    -0.53
    cohol
    -0.53
    SequentialGroup
    -0.52
    appen
    -0.51
    POSITIVE LOGITS
    <bos>
    0.71
    脚注の使い方
    0.61
    ſelf
    0.60
    XmlAccessType
    0.59
    GrantedAuthority
    0.59
    قایناق‌لار
    0.56
    PDOException
    0.52
    这一幕
    0.52
    insics
    0.51
    ListItemIcon
    0.50
    Activations Density 1.565%

    No Known Activations