© 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. 14364
    Prev
    Next
    INDEX
    Explanations

    words related to business performance

    oai_token-act-pair · gemini-2.0-flash

    Business, Finance

    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
     للمعارف
    -0.59
    AddTagHelper
    -0.58
    таратура
    -0.51
    /***/
    -0.51
    اریخ
    -0.50
    rénées
    -0.49
     Squash
    -0.48
    ndt
    -0.48
    RefNanny
    -0.47
    \{\\
    -0.47
    POSITIVE LOGITS
    原始内容存档于
    0.60
     لينك
    0.53
    ::_('
    0.50
    ($__
    0.49
     '{@
    0.48
    RetentionPolicy
    0.47
    Zeneca
    0.47
     Corbu
    0.47
    "><!--
    0.47
    dicionado
    0.47
    Activations Density 4.083%

    No Known Activations