© 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. 467
    Prev
    Next
    INDEX
    Explanations

    mentions of politics or controversial social issues, especially associating them with specific people or institutions.

    oai_token-act-pair · gemini-2.0-flash

    Mentions of 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
    ########.
    -0.65
    <bos>
    -0.65
     estimés
    -0.57
    허
    -0.56
    PRWEB
    -0.55
     disponibilités
    -0.55
     referrerpolicy
    -0.55
     pinulongan
    -0.53
    GraphicsUnit
    -0.52
    ГЛА
    -0.52
    POSITIVE LOGITS
     Syndrome
    0.55
     Glance
    0.54
    ững
    0.54
     Mundi
    0.52
     Mania
    0.52
    sprache
    0.51
     Futebol
    0.50
     Bowl
    0.50
    Dome
    0.49
     Leagues
    0.49
    Activations Density 15.503%

    No Known Activations