© 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. 3113
    Prev
    Next
    INDEX
    Explanations

    phrasal verbs whose second part is 'down'

    oai_token-act-pair · gemini-2.0-flash

    reduce, reducing, reduced

    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
    كذا
    -0.54
    AxisAlignment
    -0.48
    才是
    -0.47
    $_['
    -0.46
     proib
    -0.46
    ENSIS
    -0.45
    FormTagHelper
    -0.45
    lní
    -0.45
    руя
    -0.44
     dringend
    -0.44
    POSITIVE LOGITS
     reduced
    1.49
     Reduced
    1.34
    reduced
    1.29
     reduction
    1.26
    Reduced
    1.25
     reducing
    1.22
     reduce
    1.21
     reduces
    1.20
     Reducing
    1.19
     Reduction
    1.17
    Activations Density 1.922%

    No Known Activations