© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5003
    Prev
    Next
    INDEX
    Explanations

    financial, political, and organizational entities, especially banks.

    oai_token-act-pair · gemini-2.0-flash

    banking and finance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    umpad
    -0.42
    VAO
    -0.42
    tvguidetime
    -0.41
    quoise
    -0.40
     Coffey
    -0.40
     hibernate
    -0.39
    ayage
    -0.38
    ChatColor
    -0.38
    PMailer
    -0.38
    red
    -0.37
    POSITIVE LOGITS
    ImageContext
    0.81
    RenderAtEndOf
    0.78
    IUrlHelper
    0.71
     ThemeData
    0.70
     للمعارف
    0.69
     Вікі
    0.68
    ".
    0.67
     насељу
    0.66
    mergeFrom
    0.66
    исленность
    0.65
    Activations Density 13.110%

    No Known Activations