© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10720
    Prev
    Next
    INDEX
    Explanations

    tokens that appear as part of hyphenated phrases or in the phrase "case by case"

    oai_token-act-pair · gemini-2.0-flash

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    々と
    -0.56
    々に
    -0.56
    々
    -0.55
     can
    -0.51
     toto
    -0.50
    ileo
    -0.49
    々が
    -0.48
    titi
    -0.48
     simply
    -0.47
     Jr
    -0.47
    POSITIVE LOGITS
     ModelExpression
    0.83
     Профиль
    0.71
     disambiguazione
    0.71
    findpost
    0.70
    principalColumn
    0.69
     AssemblyProduct
    0.69
    batore
    0.68
    ngrx
    0.67
     propOrder
    0.66
     compagni
    0.66
    Activations Density 0.749%

    No Known Activations