© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11471
    Prev
    Next
    INDEX
    Explanations

    words from the Croatian language

    oai_token-act-pair · gemini-2.0-flash

    foreign language

    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
    -------
    -0.55
     Rao
    -0.54
     сумка
    -0.49
     numerus
    -0.49
     ?>"
    -0.48
    matum
    -0.47
    =$?
    -0.47
    klart
    -0.47
     hilsen
    -0.47
     onComplete
    -0.46
    POSITIVE LOGITS
     /\.
    0.69
    SourceChecksum
    0.67
    DrawerToggle
    0.65
    NgModule
    0.64
    HtmlAttribute
    0.60
    ⓧ
    0.60
    awtextra
    0.60
    Geplaatst
    0.59
    ########.
    0.58
     redistribute
    0.58
    Activations Density 0.073%

    No Known Activations