© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13592
    Prev
    Next
    INDEX
    Explanations

    mentions of Clackmannanshire and Dunblane in a political context

    oai_token-act-pair · gemini-2.0-flash

    Scotland locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     necrosis
    -0.57
     Hippo
    -0.56
     '{@
    -0.55
    Odkazy
    -0.55
    orale
    -0.55
     Fotografie
    -0.53
     OpenStreetMap
    -0.52
     flotation
    -0.52
     naturelles
    -0.50
    ostock
    -0.50
    POSITIVE LOGITS
    SBATCH
    0.66
     pinulongan
    0.65
     يتيمه
    0.53
    Personensuche
    0.52
     חיצוניים
    0.51
    AttributeSet
    0.51
    DataAnnotations
    0.50
    省市镇
    0.50
    SharedCtor
    0.49
    rungsseite
    0.49
    Activations Density 0.437%

    No Known Activations