© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6520
    Prev
    Next
    INDEX
    Explanations

    variants of the word "will" or "would"

    oai_token-act-pair · gemini-2.0-flash

    tokens starting with 't'

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

    Negations

    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
    verwijspagina
    -0.81
    OGND
    -0.76
    ########.
    -0.74
    expandindo
    -0.71
     photolibrary
    -0.70
     zvuky
    -0.68
     itſelf
    -0.68
     BIBSYS
    -0.68
     Jefus
    -0.68
    CodedInputStream
    -0.66
    POSITIVE LOGITS
     M
    0.45
     San
    0.43
     узна
    0.41
     karşılaş
    0.41
     A
    0.41
     مرد
    0.40
     ever
    0.40
     m
    0.40
     vittoria
    0.39
     b
    0.39
    Activations Density 2.607%

    No Known Activations