© 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. 13010
    Prev
    Next
    INDEX
    Explanations

    testimony in a police investigation

    oai_token-act-pair · gemini-2.0-flash

    Swaziland/South Africa legal cases

    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
     ModelExpression
    -0.75
    setVerticalGroup
    -0.73
     Roskov
    -0.73
     femininas
    -0.68
     propOrder
    -0.67
    Ārējās
    -0.67
     estekak
    -0.65
    TintMode
    -0.65
    RegistryLite
    -0.64
    HideFlags
    -0.64
    POSITIVE LOGITS
    we
    0.59
    li
    0.55
    tu
    0.51
    he
    0.50
    bi
    0.50
    se
    0.49
    i
    0.49
    ta
    0.49
     Wali
    0.48
     Ndi
    0.48
    Activations Density 11.661%

    No Known Activations