© 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. 7414
    Prev
    Next
    INDEX
    Explanations

    words related to choices, decisions, either/or situations, and the mind

    oai_token-act-pair · gemini-2.0-flash

    code or programming terminology

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

    cking

    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
    .
    -0.63
    extField
    -0.63
    
    -0.54
    principalColumn
    -0.53
     transfieras
    -0.52
    em
    -0.50
     gebra
    -0.49
    would
    -0.48
    。
    -0.48
    UITableViewCell
    -0.48
    POSITIVE LOGITS
     AssemblyCulture
    0.68
    })$}
    0.55
    dialement
    0.55
    usammen
    0.54
     }}$}
    0.53
    collant
    0.52
     vectorielle
    0.50
     useParams
    0.50
     ensaio
    0.50
    ltk
    0.49
    Activations Density 18.893%

    No Known Activations