© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11178
    Prev
    Next
    INDEX
    Explanations

    language related to financial guidelines

    oai_token-act-pair · gemini-2.0-flash

    finances and legal matters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     disambiguazione
    -0.74
     unknownFields
    -0.73
    клопе
    -0.72
     transfieras
    -0.69
     المعيارى
    -0.67
     makeStyles
    -0.66
    WebElementEntity
    -0.65
    SourceChecksum
    -0.64
     CreateTagHelper
    -0.63
     externi
    -0.63
    POSITIVE LOGITS
     drop
    0.53
    endpush
    0.52
     god
    0.51
    god
    0.49
     St
    0.46
    CancelButton
    0.45
     st
    0.45
     Drop
    0.45
    drop
    0.44
     Medium
    0.43
    Activations Density 2.491%

    No Known Activations