© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 14719
    Prev
    Next
    INDEX
    Explanations

    terms related to writing and stories, including story elements, characters, and the act of reading

    oai_token-act-pair · gemini-2.0-flash

    reader

    np_max-act · gemini-2.0-flash

    reader

    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_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     snippetHide
    -0.63
    slidesToShow
    -0.63
     sauvages
    -0.60
    férence
    -0.57
    >>()
    -0.56
    SpringBootTest
    -0.56
    Czytaj
    -0.56
     fince
    -0.55
    ImGui
    -0.54
     pylint
    -0.54
    POSITIVE LOGITS
    AddTagHelper
    0.63
     незавершена
    0.56
     gynhyrchwyd
    0.56
     subjek
    0.55
    uxxxx
    0.55
    abestanden
    0.54
    scriptcase
    0.52
    TabIndex
    0.52
    ValueStyle
    0.52
     propOrder
    0.51
    Activations Density 2.049%

    No Known Activations