© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13556
    Prev
    Next
    INDEX
    Explanations

    text that is a quotation

    oai_token-act-pair · gemini-2.0-flash

    quote

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     quote
    -2.33
     quoted
    -2.28
     quotes
    -2.17
     Quote
    -2.06
    Quote
    -2.03
    quote
    -1.98
     quotation
    -1.97
     quoting
    -1.96
     quotations
    -1.95
     QUOTE
    -1.88
    POSITIVE LOGITS
     الرياضيه
    0.65
     continúas
    0.57
    IsRequired
    0.56
    وحة
    0.53
     PETERS
    0.51
     것이다
    0.50
     مرئيه
    0.49
    sile
    0.49
    AddTagHelper
    0.49
     désert
    0.49
    Activations Density 2.741%

    No Known Activations