© 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. 11540
    Prev
    Next
    INDEX
    Explanations

    quantifiers and time duration

    oai_token-act-pair · gemini-2.0-flash

    phrases involving quantities or amounts

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

    past events

    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
     some
    -1.50
     portion
    -1.40
    some
    -1.37
     portions
    -1.22
    Some
    -1.21
     Portion
    -1.21
     Some
    -1.19
    portion
    -1.16
     SOME
    -1.09
     majority
    -1.09
    POSITIVE LOGITS
    setVerticalGroup
    0.65
    WireFormatLite
    0.61
    Geplaatst
    0.59
    semantics
    0.59
     of
    0.57
    enumi
    0.55
    исленность
    0.51
     NavController
    0.47
     isInitialized
    0.46
    TabIndex
    0.46
    Activations Density 1.934%

    No Known Activations