© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15235
    Prev
    Next
    INDEX
    Explanations

    words associated with commercial exchange or business transactions and certain manufactured devices.

    oai_token-act-pair · gemini-2.0-flash

    service

    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
    ьаж
    -0.77
    RenderAtEndOf
    -0.76
    WebElementEntity
    -0.74
    apunov
    -0.67
    jsonwebtoken
    -0.60
     umane
    -0.59
     blessés
    -0.58
     Ause
    -0.56
     fraî
    -0.53
     neuve
    -0.52
    POSITIVE LOGITS
     service
    2.73
     Service
    2.44
    service
    2.34
    Service
    2.30
     SERVICE
    2.20
    SERVICE
    2.05
    ervice
    1.88
     servicio
    1.76
     serviço
    1.64
     services
    1.63
    Activations Density 3.275%

    No Known Activations