© 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. 12360
    Prev
    Next
    INDEX
    Explanations

    words related to corporate structure and responsibilities.

    oai_token-act-pair · gemini-2.0-flash

    business, companies, management

    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
    Personendaten
    -0.97
     Signalez
    -0.78
     мәкал
    -0.76
     ModelExpression
    -0.75
     Paglinawan
    -0.74
     Efq
    -0.73
    RenderAtEndOf
    -0.71
    Hochspringen
    -0.67
     RouterModule
    -0.66
    exitRule
    -0.66
    POSITIVE LOGITS
    IntentFilter
    0.57
     приго
    0.44
     corrientes
    0.43
     Leader
    0.43
     financière
    0.43
     líderes
    0.43
     disposição
    0.42
     parques
    0.42
     början
    0.42
     boîtes
    0.42
    Activations Density 3.587%

    No Known Activations