© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12398
    Prev
    Next
    INDEX
    Explanations

    documents related to tax

    oai_token-act-pair · gemini-2.0-flash

    tax

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     MainAxisSize
    -1.01
    Демографія
    -0.72
     AttributeSet
    -0.71
    RenderAtEndOf
    -0.70
    ChildScrollView
    -0.68
     ThemeData
    -0.66
    WebVitals
    -0.66
     المعيارى
    -0.66
     InputDecoration
    -0.65
     незавершена
    -0.64
    POSITIVE LOGITS
    RegressionTest
    0.74
    estacks
    0.54
    IsContent
    0.51
     flats
    0.46
    falle
    0.45
    alnız
    0.44
    resultCode
    0.44
     cortes
    0.44
     tribunal
    0.44
    getTarget
    0.43
    Activations Density 2.012%

    No Known Activations