© 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. 6392
    Prev
    Next
    INDEX
    Explanations

    words relating to people and societal/political groups or entities.

    oai_token-act-pair · gemini-2.0-flash

    people

    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
    లాలు
    -0.78
    doesn
    -0.65
    needs
    -0.64
    wants
    -0.63
    PreferredItem
    -0.63
    XMLSchema
    -0.60
    need
    -0.58
    basicConfig
    -0.56
    have
    -0.56
    sempre
    -0.56
    POSITIVE LOGITS
    ']")
    0.52
    TagMode
    0.49
    createTextNode
    0.49
    0.47
    цездатний
    0.47
     esboço
    0.46
    rawDesc
    0.46
     RVA
    0.45
    odes
    0.45
     Mexicano
    0.45
    Activations Density 7.359%

    No Known Activations