© 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. 1818
    Prev
    Next
    INDEX
    Explanations

    discussions or mentions of politics, business and associated negative concepts (e.g. corruption, radicalism).

    oai_token-act-pair · 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
    ViewFeatures
    -0.59
     iprot
    -0.56
    انجليز
    -0.55
    RTDA
    -0.55
    Adop
    -0.53
     adopt
    -0.53
    adopted
    -0.52
    naeus
    -0.51
     adoptar
    -0.51
    LookAnd
    -0.50
    POSITIVE LOGITS
    TestingModule
    0.58
     للمعارف
    0.56
    Архівовано
    0.55
    tagHelper
    0.54
    BuilderFactory
    0.52
     CreateTagHelper
    0.52
    uminescence
    0.52
    BeginContext
    0.51
    ГЛА
    0.51
     trajets
    0.50
    Activations Density 7.661%

    No Known Activations