© 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. 3264
    Prev
    Next
    INDEX
    Explanations

    mentions of legal or financial capital

    oai_token-act-pair · gemini-2.0-flash

    capital

    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
     capital
    -3.19
     Capital
    -2.92
    Capital
    -2.91
     CAPITAL
    -2.77
    capital
    -2.77
    CAPITAL
    -2.47
     capitol
    -2.19
     capitals
    -2.16
     capitale
    -2.03
     capitalized
    -1.99
    POSITIVE LOGITS
    RectangleBorder
    0.58
    formik
    0.55
     Puck
    0.48
    }$)
    0.44
     puck
    0.44
    RTLI
    0.44
    Formik
    0.43
    uncur
    0.43
     Normdatei
    0.42
    essler
    0.42
    Activations Density 1.763%

    No Known Activations