© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11060
    Prev
    Next
    INDEX
    Explanations

    proper nouns associated with political situations.

    oai_token-act-pair · gemini-2.0-flash

    Kings and rulers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     fichas
    -0.46
    enoord
    -0.45
     lourdes
    -0.45
    iconductor
    -0.44
    athione
    -0.44
     perus
    -0.44
     pape
    -0.43
    érc
    -0.42
     Référence
    -0.41
     وصف
    -0.41
    POSITIVE LOGITS
    AndEndTag
    0.94
     chiefs
    0.75
     createContext
    0.75
    ControllerAdvice
    0.75
    oa̍t
    0.73
    +#+#
    0.71
    WebVitals
    0.70
     kingdoms
    0.68
    Дереккөздер
    0.65
    Sklici
    0.64
    Activations Density 1.253%

    No Known Activations