© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3740
    Prev
    Next
    INDEX
    Explanations

    words related to government, organizations, and projects, often involving collaboration and information sharing

    oai_token-act-pair · gemini-2.0-flash

    Especially

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    migrationBuilder
    -0.75
     TextInputType
    -0.72
    enumii
    -0.69
    __':
    -0.69
     ISNI
    -0.69
     CascadeType
    -0.69
    Ārējās
    -0.68
    orianCalendar
    -0.68
     MainAxisSize
    -0.67
     يتيمه
    -0.66
    POSITIVE LOGITS
     especially
    0.59
     Especially
    0.56
    Especially
    0.55
     terutama
    0.54
     ungefär
    0.53
     specialmente
    0.51
     särskilt
    0.51
     særlig
    0.50
     especialmente
    0.50
     particularly
    0.50
    Activations Density 2.587%

    No Known Activations