© 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. 14136
    Prev
    Next
    INDEX
    Explanations

    adjectives that describe importance or state

    oai_token-act-pair · gemini-2.0-flash

    Important elements

    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
     sources
    -1.82
     Sources
    -1.73
     source
    -1.73
    sources
    -1.67
    Sources
    -1.55
     Source
    -1.54
     SOURCE
    -1.53
    source
    -1.48
    Source
    -1.44
     SOURCES
    -1.41
    POSITIVE LOGITS
    iprot
    0.45
     Projektu
    0.43
     Ramos
    0.42
    deserialize
    0.42
    tivitas
    0.42
    damas
    0.42
    ifrance
    0.42
    ituaries
    0.41
    trie
    0.41
     gerekiyor
    0.41
    Activations Density 4.586%

    No Known Activations