© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2770
    Prev
    Next
    INDEX
    Explanations

    text towards the ends of sentences, after punctuation marks, or that ends paragraphs

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     متعلقه
    -1.18
     nahilalakip
    -1.11
     CreateTagHelper
    -1.05
     دیکھیے
    -1.05
    ImageContext
    -1.02
     Signalez
    -1.02
    expandindo
    -1.01
     мәкал
    -0.98
     defaultstate
    -0.97
     EconPapers
    -0.96
    POSITIVE LOGITS
    so
    0.52
    for
    0.48
     A
    0.47
     The
    0.47
    if
    0.46
    based
    0.45
     An
    0.45
    ся
    0.45
    ir
    0.44
    read
    0.44
    Activations Density 3.222%

    No Known Activations