© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14064
    Prev
    Next
    INDEX
    Explanations

    uses of the word 'know', 'notice', and 'recall'

    oai_token-act-pair · gemini-2.0-flash

    remembering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    yx
    -0.52
    bach
    -0.45
     بات
    -0.43
    zio
    -0.43
    artz
    -0.43
     Southern
    -0.43
    cel
    -0.42
    kez
    -0.42
    enda
    -0.42
    klaim
    -0.42
    POSITIVE LOGITS
    ImageContext
    1.00
    RenderAtEndOf
    0.85
    AddTagHelper
    0.83
    ArgsConstructor
    0.81
    tagHelperRunner
    0.80
    ConstraintMaker
    0.75
     AssemblyCulture
    0.73
    featureID
    0.71
     mergeFrom
    0.70
    richTextPanel
    0.69
    Activations Density 1.010%

    No Known Activations