© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12391
    Prev
    Next
    INDEX
    Explanations

    references to aircraft like Japanese Nakajima Ki-43 and Grumman F6F Hellcat fighter planes, including hyphenated id numbers

    oai_token-act-pair · gemini-2.0-flash

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    Erreferentziak
    -0.59
    ξύ
    -0.59
    rawdę
    -0.58
     leksikon
    -0.58
    APOLIS
    -0.58
    tett
    -0.57
    Demografia
    -0.57
    GraphicsUnit
    -0.57
    OGND
    -0.57
     interviewer
    -0.57
    POSITIVE LOGITS
    IUrlHelper
    0.60
    SourceChecksum
    0.54
    økt
    0.52
     battu
    0.52
     mukana
    0.51
     conciencia
    0.50
     Normdatei
    0.50
     urbain
    0.47
     varmt
    0.47
    makeConstraints
    0.46
    Activations Density 0.850%

    No Known Activations