© 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. 3490
    Prev
    Next
    INDEX
    Explanations

    financial and legal jargon, especially amounts of money

    oai_token-act-pair · gemini-2.0-flash

    $

    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
     <<<<<<<<<<<<<<
    -0.58
    diers
    -0.49
    clusal
    -0.48
     régionales
    -0.47
     say
    -0.47
    cemment
    -0.47
    ственно
    -0.46
    ktur
    -0.44
    Ouverture
    -0.44
     δη
    -0.43
    POSITIVE LOGITS
    DockStyle
    0.75
    oredCriteria
    0.75
     مرئيه
    0.73
    :✨
    0.69
     '{@
    0.67
    ($__
    0.66
    ThroughAttribute
    0.62
    adaptiveStyles
    0.61
    XmlAccessType
    0.59
     transfieras
    0.57
    Activations Density 3.705%

    No Known Activations