© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4226
    Prev
    Next
    INDEX
    Explanations

    adjectives and adverbs that denote size, quantity, or degree

    oai_token-act-pair · gemini-2.0-flash

    quantity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     lots
    -0.60
     plenty
    -0.57
     Plenty
    -0.55
    lots
    -0.54
     Lots
    -0.53
    Plenty
    -0.52
     alot
    -0.52
    Lots
    -0.50
     such
    -0.50
    WireFormat
    -0.50
    POSITIVE LOGITS
    tagHelperRunner
    0.77
    SuccessListener
    0.76
    SequentialGroup
    0.73
    ularity
    0.68
    DoubleQuotes
    0.65
     ExecuteAsync
    0.64
     EconPapers
    0.63
    Autoritní
    0.60
    hyrchwyd
    0.60
    RepeatedField
    0.60
    Activations Density 1.999%

    No Known Activations