© 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. 7258
    Prev
    Next
    INDEX
    Explanations

    the word "out" and the prefix "in-"

    oai_token-act-pair · gemini-2.0-flash

    out

    np_max-act · 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
     domestiques
    -0.54
     coach
    -0.52
    AnchorStyles
    -0.51
    CardContent
    -0.51
    ędzie
    -0.49
     żyw
    -0.49
     Isaacs
    -0.48
     coaches
    -0.48
     machine
    -0.47
    bois
    -0.47
    POSITIVE LOGITS
     كومونز
    0.87
     الحره
    0.78
     nahilalakip
    0.73
    (!__
    0.70
    AddTagHelper
    0.67
    ValueStyle
    0.66
    ConstraintMaker
    0.65
    ViewFeatures
    0.64
    OGND
    0.64
    cshtml
    0.64
    Activations Density 1.206%

    No Known Activations