© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13502
    Prev
    Next
    INDEX
    Explanations

    words associated with academic research, statistical analysis, professional sports and weaponry

    oai_token-act-pair · gemini-2.0-flash

    topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    AutoScale
    -0.49
    PerformLayout
    -0.45
    StructEnd
    -0.43
    GEBURTSDATUM
    -0.43
    UnknownFieldSet
    -0.38
     mostrarán
    -0.37
    enterOuterAlt
    -0.35
     parseFrom
    -0.34
    AutoScaleMode
    -0.34
     внимания
    -0.34
    POSITIVE LOGITS
     الحره
    0.90
     UIKit
    0.69
    uttavia
    0.66
    ugier
    0.65
    andaag
    0.64
    TagHelper
    0.64
    kmal
    0.64
    قلال
    0.63
    ]--;
    0.62
    favourable
    0.60
    Activations Density 23.497%

    No Known Activations