© 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. 5759
    Prev
    Next
    INDEX
    Explanations

    words pertaining to finance/stock market

    oai_token-act-pair · gemini-2.0-flash

    specific detailed information

    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
     démocr
    -0.59
     quelcon
    -0.59
    Aero
    -0.56
     astra
    -0.55
    mopolitan
    -0.54
     Aero
    -0.54
     cérami
    -0.54
     paleo
    -0.54
     rhino
    -0.53
     Dyna
    -0.51
    POSITIVE LOGITS
     gr
    0.51
     burn
    0.46
    gr
    0.46
     bag
    0.45
     burns
    0.45
     burning
    0.45
     pads
    0.44
     realization
    0.44
     ward
    0.44
     dust
    0.43
    Activations Density 3.264%

    No Known Activations