© 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. 6249
    Prev
    Next
    INDEX
    Explanations

    words and phrases commonly found in journalistic or political writing.

    oai_token-act-pair · gemini-2.0-flash

    organizations

    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
     company
    -2.42
    company
    -2.16
     Company
    -2.13
     COMPANY
    -2.08
    Company
    -2.06
    COMPANY
    -1.88
     companies
    -1.73
     Companies
    -1.55
    公司
    -1.53
    Companies
    -1.52
    POSITIVE LOGITS
    Geografia
    0.46
    Égypte
    0.40
    מר
    0.40
     Mejora
    0.39
    apyrus
    0.39
    MethodManager
    0.38
    Suara
    0.38
    viewDid
    0.38
     sahiptir
    0.38
     Palgrave
    0.37
    Activations Density 6.555%

    No Known Activations