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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1560
    Prev
    Next
    INDEX
    Explanations

    references to the American South.

    oai_token-act-pair · gemini-2.0-flash

    American South

    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
     North
    -1.99
     Southern
    -1.97
     South
    -1.95
    South
    -1.91
     southern
    -1.87
    SOUTH
    -1.86
     SOUTH
    -1.86
    Southern
    -1.85
    North
    -1.84
     south
    -1.79
    POSITIVE LOGITS
     ElementRef
    0.52
    }(),
    0.44
    WriteAttribute
    0.40
    kwds
    0.40
    andaş
    0.40
     merveille
    0.39
    newArrayList
    0.39
    Zacks
    0.39
    ureka
    0.39
     leuk
    0.39
    Activations Density 1.628%

    No Known Activations