© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6835
    Prev
    Next
    INDEX
    Explanations

    Dutch words related to scientific funding organizations

    oai_token-act-pair · gemini-2.0-flash

    Non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    AndEndTag
    -0.54
    reide
    -0.52
    tvguidetime
    -0.47
    ibol
    -0.47
     ligiloj
    -0.46
    vern
    -0.46
    oa̍t
    -0.46
    ћ
    -0.45
    dian
    -0.44
    writeFieldEnd
    -0.43
    POSITIVE LOGITS
    Personendaten
    0.61
    criture
    0.59
    ياء
    0.58
    InvalidProtocol
    0.58
     يتيمه
    0.56
    OrBuilder
    0.54
     ArrayAdapter
    0.54
    toggler
    0.54
     aceptas
    0.54
    addCriterion
    0.54
    Activations Density 0.136%

    No Known Activations