© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3336
    Prev
    Next
    INDEX
    Explanations

    phrases implying positive or negative comparisons relating to difficult or embarrassing things

    oai_token-act-pair · gemini-2.0-flash

    advice/personal situations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     manqué
    -0.55
    #{
    -0.54
     AssemblyCulture
    -0.53
     makeStyles
    -0.51
    nativeElement
    -0.51
     Photographie
    -0.50
     möglich
    -0.46
    NgModule
    -0.46
     NgModule
    -0.45
     directe
    -0.45
    POSITIVE LOGITS
     विश्वसनीयता
    0.73
     informée
    0.68
     EconPapers
    0.68
    ngths
    0.67
    setopt
    0.64
    ViewFeatures
    0.60
    Diweddarwch
    0.60
    principalTable
    0.60
    endregion
    0.60
    typeparam
    0.60
    Activations Density 1.568%

    No Known Activations