© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12304
    Prev
    Next
    INDEX
    Explanations

    a variety of tokens including math symbols, code snippets, tax related terms, and some words followed by digits.

    oai_token-act-pair · gemini-2.0-flash

    say "G" words

    np_max-act-logits · gemini-2.0-flash

    say "g" words

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    IVEREF
    -0.70
    MLLoader
    -0.60
    calipsis
    -0.60
    jooq
    -0.59
    CloseOperation
    -0.58
     cherchés
    -0.58
     nahilalakip
    -0.57
     Référence
    -0.57
     unknownFields
    -0.56
    ConstraintMaker
    -0.56
    POSITIVE LOGITS
     GS
    1.33
     GG
    1.30
    GP
    1.28
     GC
    1.27
     GR
    1.27
     GP
    1.26
     Gs
    1.25
     G
    1.24
     GF
    1.23
    GF
    1.23
    Activations Density 12.012%

    No Known Activations