© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5606
    Prev
    Next
    INDEX
    Explanations

    language related to finance, news, and opinions

    oai_token-act-pair · gemini-2.0-flash

    financial

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    RenderAtEndOf
    -0.73
     nakalista
    -0.65
    يميديا
    -0.61
     onPostExecute
    -0.61
    ácara
    -0.58
     Administrativna
    -0.57
    Rozmiar
    -0.56
     Référence
    -0.55
    oader
    -0.54
    bewerken
    -0.54
    POSITIVE LOGITS
     financial
    2.70
    financial
    2.33
     Financial
    2.33
    Financial
    2.31
     FINANCIAL
    2.09
    FINANCIAL
    1.95
     finance
    1.91
     financiera
    1.70
     Finance
    1.67
    finance
    1.66
    Activations Density 5.584%

    No Known Activations