© 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. 2193
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate someone is being duplicitous, followed by context where someone turned his back to the judge

    oai_token-act-pair · gemini-2.0-flash

    back

    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
    ngdoc
    -0.64
     status
    -0.64
    InSection
    -0.60
     Offisielt
    -0.60
    stateProvider
    -0.60
     Status
    -0.57
    XmlAccessType
    -0.57
     vPvB
    -0.56
    tangentMode
    -0.54
     المعيارى
    -0.54
    POSITIVE LOGITS
     backs
    1.28
    backs
    1.09
     back
    1.09
    back
    0.99
    BACK
    0.91
    Back
    0.84
     Back
    0.80
     BACK
    0.77
     Rücken
    0.75
    backed
    0.73
    Activations Density 0.861%

    No Known Activations