© 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. 13782
    Prev
    Next
    INDEX
    Explanations

    place names, particularly names of cities and regions, often including associated abbreviations or related terms

    oai_token-act-pair · gemini-2.0-flash

    non-english text and 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_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
     élevés
    -0.41
     particuliers
    -0.39
     élevées
    -0.38
     variés
    -0.37
     colgantes
    -0.37
     contribué
    -0.36
     ziua
    -0.36
     actuelles
    -0.35
     gestión
    -0.35
     viață
    -0.34
    POSITIVE LOGITS
     Theſe
    1.16
    ſelves
    1.13
     iſt
    1.11
     itſelf
    1.11
     ―――――
    1.10
    存于互联网档案馆
    1.07
     Reſ
    1.06
     myſelf
    1.05
     Anſ
    1.05
     Houſe
    1.05
    Activations Density 8.172%

    No Known Activations