© 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. 9696
    Prev
    Next
    INDEX
    Explanations

    locations, especially those modified by prepositional relationships

    oai_token-act-pair · gemini-2.0-flash

    locations and names

    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
    AutoScale
    -0.48
    \{\\
    -0.47
    TypedDataSet
    -0.44
     Rule
    -0.43
     aard
    -0.43
    bit
    -0.41
     Tons
    -0.41
    diad
    -0.40
     Thumbnails
    -0.40
    rinos
    -0.40
    POSITIVE LOGITS
    MLLoader
    0.67
    esgue
    0.66
    Datuak
    0.62
     besök
    0.60
     Stal
    0.58
    awtextra
    0.57
     Illy
    0.55
    findpost
    0.54
    seamnă
    0.53
    }.
    0.52
    Activations Density 0.286%

    No Known Activations