© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7351
    Prev
    Next
    INDEX
    Explanations

    words that describe qualities or characteristics

    oai_token-act-pair · gemini-2.0-flash

    white

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    abestanden
    -0.77
    IsInitialized
    -0.72
     StatelessWidget
    -0.71
    
    -0.70
    migrationBuilder
    -0.69
     populated
    -0.66
     convertView
    -0.64
     Ouv
    -0.63
    AppMethodBeat
    -0.63
    تقاوى
    -0.63
    POSITIVE LOGITS
     white
    0.85
     White
    0.82
    White
    0.77
    white
    0.72
     WHITE
    0.70
     cold
    0.59
    WHITE
    0.59
     trắng
    0.58
    白色的
    0.56
    whitespace
    0.55
    Activations Density 0.730%

    No Known Activations