© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11826
    Prev
    Next
    INDEX
    Explanations

    words related to financial and business matters, particularly in the food industry, and general commercial activities

    oai_token-act-pair · gemini-2.0-flash

    legal/financial/business content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Moines
    -0.50
    phrine
    -0.45
     czę
    -0.45
     estufa
    -0.44
     Melo
    -0.43
    ingat
    -0.43
     counter
    -0.42
     давно
    -0.40
    atoshi
    -0.40
     Häufig
    -0.40
    POSITIVE LOGITS
    exitRule
    1.16
    Referencie
    0.94
    ⓧ
    0.92
     متعلقه
    0.88
     snippetHide
    0.82
     nakalista
    0.80
    Rhestr
    0.77
     rospy
    0.75
     bezeichneter
    0.75
     AssemblyCulture
    0.74
    Activations Density 1.225%

    No Known Activations