© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10574
    Prev
    Next
    INDEX
    Explanations

    long conjunctions of clauses and phrases

    oai_token-act-pair · gemini-2.0-flash

    Technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    Geplaatst
    -0.50
    Autoritní
    -0.47
     OMITBAD
    -0.47
     AssemblyCompany
    -0.44
    gway
    -0.44
     CONSIDERATIONS
    -0.43
     Internacional
    -0.43
    antaine
    -0.42
     geogra
    -0.42
    тей
    -0.41
    POSITIVE LOGITS
    tvguidetime
    0.71
    ReusableCell
    0.64
     resourceCulture
    0.64
    ագրություններ
    0.63
    CESO
    0.61
    ochond
    0.57
    titleMargin
    0.57
     GoogleFonts
    0.56
     Audiodateien
    0.56
    essions
    0.54
    Activations Density 6.563%

    No Known Activations