© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4158
    Prev
    Next
    INDEX
    Explanations

    a mix of seemingly disparate elements relating to inventions, embedded systems, and tabular data

    oai_token-act-pair · gemini-2.0-flash

    technical documents/patents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    Transcription
    -0.53
    lorem
    -0.52
    mem
    -0.51
    GEBURTS
    -0.46
     pull
    -0.45
    Transkript
    -0.44
    วง
    -0.43
     coin
    -0.43
    Mutagenicity
    -0.43
     fine
    -0.43
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    1.00
    SourceChecksum
    0.93
     nahilalakip
    0.85
    tagHelperRunner
    0.79
     AssemblyCulture
    0.75
     defaultstate
    0.74
    Personendaten
    0.73
     AttributeSet
    0.69
    PreExecute
    0.68
    styleType
    0.68
    Activations Density 0.640%

    No Known Activations