© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15008
    Prev
    Next
    INDEX
    Explanations

    non-English text and numbers

    oai_token-act-pair · gemini-2.0-flash

    foreign language text

    np_max-act-logits · gemini-2.0-flash

    French function words

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    tagHelperRunner
    -1.11
    ngdoc
    -0.96
     Efq
    -0.95
     Monfieur
    -0.91
     ſeveral
    -0.91
    RegistryLite
    -0.90
     myſelf
    -0.87
    StructEnd
    -0.86
    parsedMessage
    -0.85
     leaſt
    -0.85
    POSITIVE LOGITS
    crites
    0.31
     fat
    0.30
    ins
    0.29
     stra
    0.29
     apost
    0.28
     ex
    0.27
     lot
    0.27
     front
    0.26
     stret
    0.26
     Tapatalk
    0.26
    Activations Density 0.606%

    No Known Activations