© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3814
    Prev
    Next
    INDEX
    Explanations

    indicators of societal systems, trends, and governmental structures plus video games

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    RectangleBorder
    -0.85
    aarrggbb
    -0.81
     InputDecoration
    -0.77
     كومونز
    -0.70
    DockStyle
    -0.69
     дописавши
    -0.69
     GoogleFonts
    -0.69
    ChildScrollView
    -0.63
     AssemblyCulture
    -0.61
     للمعارف
    -0.59
    POSITIVE LOGITS
    Branch
    0.58
     mor
    0.56
     BRANCH
    0.53
     Branch
    0.52
     branch
    0.51
     bifurcation
    0.51
     coales
    0.51
     discarded
    0.49
    ControllerAdvice
    0.48
    faces
    0.48
    Activations Density 5.019%

    No Known Activations