© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12463
    Prev
    Next
    INDEX
    Explanations

    strings of seemingly random upper-case letters and a few lower-case letters

    oai_token-act-pair · gemini-2.0-flash

    URLs and Code 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_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     GenerationType
    -0.87
     purpoſe
    -0.84
     Majefty
    -0.83
     myſelf
    -0.82
     ſtate
    -0.82
     houſe
    -0.82
     nakalista
    -0.81
    ContentAsync
    -0.81
    rungsseite
    -0.77
     pleaſure
    -0.76
    POSITIVE LOGITS
    te
    0.55
    Per
    0.46
     ihr
    0.41
    ih
    0.40
    PER
    0.39
     Per
    0.39
    ii
    0.39
    tus
    0.38
    する
    0.38
    ин
    0.38
    Activations Density 0.417%

    No Known Activations