© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9919
    Prev
    Next
    INDEX
    Explanations

    helper verbs and pronouns near adjectives

    oai_token-act-pair · gemini-2.0-flash

    Reading or viewing

    np_max-act-logits · gemini-2.0-flash
    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
    DTD
    -0.62
    matchCondition
    -0.59
    WithIOException
    -0.59
     createSprite
    -0.57
     protoimpl
    -0.56
    MENAFN
    -0.56
    DotNetBar
    -0.55
    NameInMap
    -0.54
    .*")]
    -0.53
     OMITBAD
    -0.53
    POSITIVE LOGITS
     viewing
    1.54
     reading
    1.48
    viewing
    1.31
     Viewing
    1.30
    reading
    1.30
     reviewing
    1.27
     review
    1.27
     Reading
    1.24
     read
    1.23
    Reading
    1.23
    Activations Density 3.478%

    No Known Activations