© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10082
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to accounting and taxes

    oai_token-act-pair · gemini-2.0-flash

    Tax-related documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ScopeManager
    -0.66
    DrawerToggle
    -0.64
    SerializedSize
    -0.63
    GeneratedMessage
    -0.61
    MigrationBuilder
    -0.55
     SwitchCompat
    -0.53
    tonsoft
    -0.52
     mapStateToProps
    -0.52
     Italijani
    -0.52
     jspb
    -0.51
    POSITIVE LOGITS
    basicConfig
    0.66
     متعلقه
    0.52
    AndroidJUnit
    0.50
    ControllerAdvice
    0.49
    turn
    0.48
    Itoa
    0.48
    tritt
    0.48
    gway
    0.48
    ifu
    0.47
    Turn
    0.47
    Activations Density 1.851%

    No Known Activations