© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11267
    Prev
    Next
    INDEX
    Explanations

    terms related to finance and data analysis, also picking up some terms related to baseball statistics

    oai_token-act-pair · gemini-2.0-flash

    futures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    :+:
    -0.66
    BASEPATH
    -0.62
    WriteTagHelper
    -0.60
    ädie
    -0.60
    NewRow
    -0.59
    Tikang
    -0.58
    vict
    -0.57
    uncher
    -0.57
     Infórmanos
    -0.57
     CreateTagHelper
    -0.56
    POSITIVE LOGITS
     themſelves
    0.60
     culoare
    0.56
     itſelf
    0.50
     myſelf
    0.49
     Theſe
    0.48
     stanga
    0.48
     înal
    0.48
     []:
    0.47
     theſe
    0.47
    newcommand
    0.46
    Activations Density 1.076%

    No Known Activations