© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7274
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to financial performance, sales, and market dynamics.

    oai_token-act-pair · gemini-2.0-flash

    business financials

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    UnusedPrivate
    -1.05
     فريبيس
    -0.98
    tvguidetime
    -0.98
     Efq
    -0.97
     snippetHide
    -0.95
     EconPapers
    -0.94
    دانشنامهٔ
    -0.93
     houſe
    -0.92
     ſtate
    -0.86
     otomatig
    -0.85
    POSITIVE LOGITS
     man
    0.41
    周
    0.40
    -
    0.39
     hat
    0.36
     he
    0.36
     dis
    0.34
    مكن
    0.33
    postgresql
    0.33
     supports
    0.33
     of
    0.33
    Activations Density 1.724%

    No Known Activations