© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11029
    Prev
    Next
    INDEX
    Explanations

    words related to analysis, assessment, study, projects, and wars or fights in business, medicine, nature, and politics

    oai_token-act-pair · gemini-2.0-flash

    Random article excerpts

    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
     changes
    -1.04
    changes
    -1.01
    Changes
    -0.96
     Changes
    -0.93
     CHANGES
    -0.87
    ReusableCell
    -0.81
     transfieras
    -0.77
     burns
    -0.76
    CHANGES
    -0.75
     returns
    -0.73
    POSITIVE LOGITS
     coordinates
    0.48
     opinions
    0.48
     works
    0.48
     Вікіпе
    0.47
    הערות
    0.46
    findpost
    0.46
     lever
    0.45
    GeoNames
    0.44
     occhi
    0.44
     automat
    0.43
    Activations Density 6.384%

    No Known Activations