© 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. 6667
    Prev
    Next
    INDEX
    Explanations

    first person pronouns and contractions

    oai_token-act-pair · gemini-2.0-flash

    technical terms and phrases related to application context

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

    I

    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
     souten
    -0.50
     dị
    -0.46
     better
    -0.45
    better
    -0.45
    方が
    -0.44
    ResponseBody
    -0.44
     soutenu
    -0.43
    ارج
    -0.43
    stood
    -0.42
     تد
    -0.41
    POSITIVE LOGITS
     uſe
    0.72
     find
    0.71
     ſtate
    0.70
    resave
    0.70
     تضيفلها
    0.70
     ModelExpression
    0.68
    NewUrlParser
    0.68
    ArrowToggle
    0.66
    mtrl
    0.65
    PreferredItem
    0.65
    Activations Density 0.806%

    No Known Activations