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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 13715
    Prev
    Next
    INDEX
    Explanations

    a mix of things, including the word "backward", words related to children, and words that might indicate product features.

    oai_token-act-pair · gemini-2.0-flash

    technical documentation

    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
     Efq
    -0.74
     Monfieur
    -0.73
     myſelf
    -0.73
     fhew
    -0.70
     itſelf
    -0.68
     Jefus
    -0.66
    __':
    -0.66
    RegistryLite
    -0.66
     fubject
    -0.66
     incompatibility
    -0.65
    POSITIVE LOGITS
    artifactId
    0.49
     recevrez
    0.49
    AddHtmlAttribute
    0.49
    fromnode
    0.48
    esgue
    0.48
     GeoNames
    0.48
    tinyos
    0.44
    Ự
    0.44
     Are
    0.44
     Reid
    0.43
    Activations Density 0.967%

    No Known Activations