© 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. 10947
    Prev
    Next
    INDEX
    Explanations

    a mixutre of Malay words alongside names with the suffix "ard"

    oai_token-act-pair · gemini-2.0-flash

    Non-English text

    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
    ethene
    -0.60
    Coordonnées
    -0.59
     tewas
    -0.57
     bestuur
    -0.56
     lemah
    -0.56
    variates
    -0.54
    vency
    -0.53
    ímite
    -0.53
    Dazu
    -0.53
    Datuak
    -0.52
    POSITIVE LOGITS
    Parcelize
    0.61
    DataBinding
    0.56
    HasMaxLength
    0.56
    AndEndTag
    0.56
    setDo
    0.55
     незавершена
    0.54
    reactstrap
    0.54
    ExecuteReader
    0.54
    Scénario
    0.51
    MarshalTo
    0.51
    Activations Density 0.191%

    No Known Activations