© 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. 16051
    Prev
    Next
    INDEX
    Explanations

    words and phrases about budgets, finances, and state economics

    oai_token-act-pair · gemini-2.0-flash

    budget

    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
     combineReducers
    -0.77
    Budget
    -0.64
    WebServlet
    -0.63
     Budget
    -0.63
     budget
    -0.63
     Budgets
    -0.59
     budgets
    -0.57
    AutoScaleMode
    -0.57
    budget
    -0.56
     Roskov
    -0.55
    POSITIVE LOGITS
    PyExc
    0.63
    rungsseite
    0.57
    verwijspagina
    0.56
    Packages
    0.53
    Spoiler
    0.52
     "".
    0.50
    rrggbb
    0.50
     Herm
    0.47
    cuno
    0.47
    ambilan
    0.47
    Activations Density 1.806%

    No Known Activations