© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10918
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to stock market trading and financial concepts

    oai_token-act-pair · gemini-2.0-flash

    loss

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    <bos>
    -0.56
    rungsseite
    -0.47
    ograf
    -0.43
     lu
    -0.43
    躬
    -0.42
    cores
    -0.40
     tit
    -0.40
    烙
    -0.39
     totiž
    -0.39
     useContext
    -0.39
    POSITIVE LOGITS
    ynb
    0.63
    èdia
    0.63
    Παραπομπές
    0.58
    RTEE
    0.57
    évaluateur
    0.56
     ibid
    0.55
     Supervisory
    0.55
    MVH
    0.54
    CloseOperation
    0.54
    加坡
    0.54
    Activations Density 0.252%

    No Known Activations