© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15387
    Prev
    Next
    INDEX
    Explanations

    code snippets, file paths, and Chinese characters related to dictionary compilation.

    oai_token-act-pair · gemini-2.0-flash

    nouns

    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
     Theſe
    -0.85
     myſelf
    -0.83
     étoient
    -0.77
     purpoſe
    -0.73
     poffible
    -0.73
     tranſ
    -0.71
     pleaſure
    -0.71
     ſche
    -0.71
     avoient
    -0.71
     miſ
    -0.71
    POSITIVE LOGITS
    stuff
    0.54
    person
    0.54
    theory
    0.53
    group
    0.52
    concept
    0.49
    sodium
    0.48
    plant
    0.48
    drug
    0.48
    skin
    0.48
    vehicle
    0.48
    Activations Density 0.597%

    No Known Activations