© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14684
    Prev
    Next
    INDEX
    Explanations

    references to places and ethnicities, especially in a historical context

    oai_token-act-pair · gemini-2.0-flash

    terms related to proper nouns or titles

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

    Historical and geographical texts

    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
    脚注の使い方
    -0.73
     StatelessWidget
    -0.54
     européens
    -0.54
    ArrowToggle
    -0.51
    entennial
    -0.49
    cadeira
    -0.48
     noire
    -0.46
     squir
    -0.46
    Przypisy
    -0.44
    createTextNode
    -0.44
    POSITIVE LOGITS
    Filmographie
    0.63
     Gallo
    0.61
    LEncoder
    0.57
     بيها
    0.55
    Corr
    0.55
    NORM
    0.54
     endforeach
    0.54
     NavController
    0.52
    usermodel
    0.52
     Corr
    0.51
    Activations Density 1.803%

    No Known Activations