© 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. 10425
    Prev
    Next
    INDEX
    Explanations

    various special characters, words, and punctuation often found in code or documentation.

    oai_token-act-pair · gemini-2.0-flash

    Code and licenses

    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
     now
    -1.40
     more
    -1.27
     next
    -1.25
     many
    -1.21
     most
    -1.20
     today
    -1.16
     every
    -1.16
     again
    -1.16
     later
    -1.15
     other
    -1.14
    POSITIVE LOGITS
    avigation
    0.59
     stewardship
    0.57
     createState
    0.51
     mask
    0.50
     girdle
    0.50
     custodian
    0.49
     containment
    0.49
     superstructure
    0.49
     selectivity
    0.49
    ociação
    0.48
    Activations Density 11.345%

    No Known Activations