© 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. 5225
    Prev
    Next
    INDEX
    Explanations

    mentions of public gatherings and halls.

    oai_token-act-pair · gemini-2.0-flash

    specific names and proper nouns

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

    event descriptions

    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
    setVerticalGroup
    -0.77
    fjspx
    -0.75
    __(/*!
    -0.72
    Personensuche
    -0.65
    matchCondition
    -0.65
    Datuak
    -0.63
    DataField
    -0.63
    Tikang
    -0.63
    тельств
    -0.62
     BrowserModule
    -0.60
    POSITIVE LOGITS
    LOTTE
    0.47
    Meds
    0.47
    hésite
    0.44
     the
    0.43
    Hymen
    0.43
     Mundial
    0.42
    baomidou
    0.42
    bondale
    0.42
     present
    0.42
    AntiForgeryToken
    0.42
    Activations Density 4.341%

    No Known Activations