© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8233
    Prev
    Next
    INDEX
    Explanations

    words related to medical and scientific topics, especially those concerning negative side effects.

    oai_token-act-pair · gemini-2.0-flash

    potential problems/consequences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    bootstrapcdn
    -0.68
    UnsafeEnabled
    -0.66
    errHandler
    -0.64
    yarnpkg
    -0.62
    diyesi
    -0.62
    FormTagHelper
    -0.60
     ligiloj
    -0.60
    LabelTagHelper
    -0.59
    MessageWindow
    -0.58
     Italijanski
    -0.58
    POSITIVE LOGITS
    Географи
    0.52
    ureka
    0.46
    +#+#
    0.43
     Tha
    0.43
     encan
    0.43
    ohy
    0.42
     Salam
    0.42
     Gesù
    0.42
     VIV
    0.42
     الاطلاع
    0.41
    Activations Density 5.419%

    No Known Activations