© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6455
    Prev
    Next
    INDEX
    Explanations

    words that are capitalized and may be proper nouns, including scientific names, people names, and class names from programming languages

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    frente
    -0.47
     finisher
    -0.46
    INION
    -0.46
    opcional
    -0.45
     نفسها
    -0.44
    momix
    -0.44
    ніципалі
    -0.44
    intenance
    -0.44
    mediately
    -0.43
    istive
    -0.43
    POSITIVE LOGITS
    <bos>
    0.84
    UnusedPrivate
    0.70
    SourceChecksum
    0.69
     nakalista
    0.66
    #
    0.63
    LookAnd
    0.62
    setof
    0.61
    ReusableCell
    0.57
    ))=\
    0.54
     noDo
    0.54
    Activations Density 2.260%

    No Known Activations