© 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. 13737
    Prev
    Next
    INDEX
    Explanations

    code snippets including functions, variables, and parameters, sometimes highlighting names of exceptions or errors

    oai_token-act-pair · gemini-2.0-flash

    Code/Log snippets

    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
     propOrder
    -0.80
    WebElementEntity
    -0.80
     Anſ
    -0.79
     Inſ
    -0.73
     Reſ
    -0.72
    HomeAsUpEnabled
    -0.71
     an
    -0.70
     betweenstory
    -0.70
     يتيمه
    -0.69
    +#+#
    -0.69
    POSITIVE LOGITS
     r
    0.57
     don
    0.54
     n
    0.52
     s
    0.51
     you
    0.51
     getting
    0.51
     m
    0.50
     f
    0.49
     G
    0.49
    équipement
    0.48
    Activations Density 14.695%

    No Known Activations