© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2104
    Prev
    Next
    INDEX
    Explanations

    countries, politics, agreements and war related terms

    oai_token-act-pair · gemini-2.0-flash

    geopolitical events/locations

    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
     india
    -0.77
     texas
    -0.73
     maine
    -0.72
     méxico
    -0.72
    #+#
    -0.70
     Finland
    -0.69
     espagne
    -0.69
     ireland
    -0.69
     toscana
    -0.69
    India
    -0.68
    POSITIVE LOGITS
    KURZBESCHREIBUNG
    0.43
    XmlRootElement
    0.41
    ScopeManager
    0.41
    كتشاف
    0.40
    InjectAttribute
    0.40
     userService
    0.35
     behavior
    0.35
    scalatest
    0.33
    esez
    0.33
     behaviors
    0.32
    Activations Density 13.753%

    No Known Activations