© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8461
    Prev
    Next
    INDEX
    Explanations

    sentences offering a suggestion or the "best way" to accomplish something

    oai_token-act-pair · gemini-2.0-flash

    way

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    tagHelperRunner
    -0.95
     Roskov
    -0.82
     AssemblyCulture
    -0.80
    oredCriteria
    -0.76
     surla
    -0.75
    OGND
    -0.73
    GEBURTSDATUM
    -0.72
    MessageTagHelper
    -0.72
    ItemBackground
    -0.70
    Xna
    -0.69
    POSITIVE LOGITS
    getInstance
    0.46
     to
    0.44
     of
    0.44
     besz
    0.43
    <bos>
    0.41
     insanların
    0.40
    les
    0.40
    te
    0.40
     diariamente
    0.40
     your
    0.40
    Activations Density 0.537%

    No Known Activations