© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10329
    Prev
    Next
    INDEX
    Explanations

    mentions of locations in China, possibly focusing on "Liushan".

    oai_token-act-pair · gemini-2.0-flash

    Foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ']>
    -0.50
    ')['
    -0.47
    ÑA
    -0.46
     co
    -0.46
    limsy
    -0.45
    ATOS
    -0.45
     major
    -0.44
    UDIO
    -0.44
     str
    -0.43
    EMOS
    -0.43
    POSITIVE LOGITS
    UserScript
    0.93
    ValueStyle
    0.87
    RenderAtEndOf
    0.77
    Hochspringen
    0.72
     betweenstory
    0.69
    MessageOf
    0.69
    DeleteBehavior
    0.69
     المعيارى
    0.68
     noastre
    0.68
    RetentionPolicy
    0.67
    Activations Density 1.644%

    No Known Activations