© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9761
    Prev
    Next
    INDEX
    Explanations

    words ending in "press" or "pressed" and words with the substring "licit" or "cito" or "clear"

    oai_token-act-pair · gemini-2.0-flash

    technical writing fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    NameInMap
    -0.56
    jooq
    -0.53
    oneofs
    -0.53
    LookAnd
    -0.51
    hasiswa
    -0.49
    Nummer
    -0.48
     Infórmanos
    -0.48
     AspNetCore
    -0.48
    ђа
    -0.47
     anillos
    -0.46
    POSITIVE LOGITS
     express
    1.84
     EXPRESS
    1.78
     Express
    1.74
     expression
    1.73
    Express
    1.70
     expressions
    1.69
    express
    1.65
    expressions
    1.61
     expre
    1.61
     expressing
    1.60
    Activations Density 0.425%

    No Known Activations