© 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. 7167
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to insurance policies

    oai_token-act-pair · gemini-2.0-flash

    phrases related to statistical data and insurance terms

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

    housing and insurance

    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
    elemField
    -0.70
    èdia
    -0.57
    SourceChecksum
    -0.57
    AnchorStyles
    -0.52
     незавершена
    -0.50
    featureID
    -0.48
    stopping
    -0.47
    bootstrapcdn
    -0.47
     AssemblyCulture
    -0.47
    Біографія
    -0.47
    POSITIVE LOGITS
     autorytatywna
    0.61
     استنادى
    0.58
    grand
    0.54
    ❋
    0.52
    makeConstraints
    0.52
    providedIn
    0.52
    BoxShadow
    0.52
    fara
    0.50
     AUT
    0.50
     aut
    0.50
    Activations Density 1.476%

    No Known Activations