© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11941
    Prev
    Next
    INDEX
    Explanations

    tokens related to geographical locations

    oai_token-act-pair · gemini-2.0-flash

    German cities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     BoxFit
    -0.81
    libft
    -0.78
    AddTagHelper
    -0.77
    RectangleBorder
    -0.73
    SPJ
    -0.70
    AsUp
    -0.69
    IsContent
    -0.68
     TextInputType
    -0.67
     propOrder
    -0.65
     betweenstory
    -0.64
    POSITIVE LOGITS
     Magdeburg
    0.70
     Lübeck
    0.65
     Nürnberg
    0.63
     Schleswig
    0.57
     Münster
    0.56
     Köln
    0.56
     Thü
    0.56
     Bielefeld
    0.56
     Würzburg
    0.56
     Sachsen
    0.55
    Activations Density 1.911%

    No Known Activations