© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14946
    Prev
    Next
    INDEX
    Explanations

    financial institutions and people who work for them

    oai_token-act-pair · gemini-2.0-flash

    Company names

    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
    lawayo
    -0.77
    bukkit
    -0.61
     poveznice
    -0.60
    UserScript
    -0.59
    thansa
    -0.58
    unhofer
    -0.54
    Nairobi
    -0.52
     Auckland
    -0.52
    avut
    -0.52
     setuptools
    -0.51
    POSITIVE LOGITS
     متعلقه
    0.59
    windowFixed
    0.59
     Савезне
    0.55
    writeFieldEnd
    0.51
     CreateTagHelper
    0.51
     ilmo
    0.50
    Statistiche
    0.48
    antaranya
    0.48
    Matéri
    0.47
    исленность
    0.46
    Activations Density 0.970%

    No Known Activations