© 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. 8340
    Prev
    Next
    INDEX
    Explanations

    the word "what" and pronouns

    oai_token-act-pair · gemini-2.0-flash

    what

    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
     things
    -0.82
    <bos>
    -0.58
     something
    -0.56
     Weizen
    -0.55
     Things
    -0.54
    Things
    -0.54
     cosas
    -0.53
     dingen
    -0.52
    things
    -0.52
     Something
    -0.52
    POSITIVE LOGITS
     resourceCulture
    0.91
     EconPapers
    0.84
     CreateTagHelper
    0.78
    帖最后由
    0.69
    ValueStyle
    0.65
     ModelExpression
    0.64
    ]")]
    0.62
     initComponents
    0.60
    yntaxException
    0.60
     ujednoznacz
    0.57
    Activations Density 0.880%

    No Known Activations