© 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. 12608
    Prev
    Next
    INDEX
    Explanations

    text from financial documents

    oai_token-act-pair · gemini-2.0-flash

    Legal/financial context

    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
     RSSSF
    -0.71
    tonode
    -0.71
     consultato
    -0.69
     MainAxisSize
    -0.68
    VideoCapture
    -0.67
     fubject
    -0.63
    __':
    -0.63
    __':
    -0.61
    IGraphics
    -0.61
    astéroïdes
    -0.60
    POSITIVE LOGITS
     Put
    0.54
    Put
    0.50
    put
    0.50
    Scénario
    0.49
     par
    0.49
    ple
    0.48
     call
    0.47
    helo
    0.45
    prus
    0.45
     Par
    0.44
    Activations Density 2.294%

    No Known Activations