© 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. 14575
    Prev
    Next
    INDEX
    Explanations

    words that don't seem to have a specific theme

    oai_token-act-pair · gemini-2.0-flash

    technical terms or categories

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

    related to art

    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
     awakeFromNib
    -0.49
    MemoryWarning
    -0.47
     préférable
    -0.47
    ว
    -0.46
     CGPoint
    -0.45
     Material
    -0.45
    usen
    -0.45
     FileNotFound
    -0.45
    ziest
    -0.45
     $#
    -0.44
    POSITIVE LOGITS
    ImageContext
    0.90
    parsedMessage
    0.73
    GEBURTSDATUM
    0.61
     AssemblyProduct
    0.60
     ModelExpression
    0.59
    XtraReports
    0.58
     codex
    0.56
    aarrggbb
    0.55
     EconPapers
    0.55
    <bos>
    0.54
    Activations Density 5.128%

    No Known Activations