© 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
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 13395
    Prev
    Next
    INDEX
    Explanations

    the word "to" followed by a verb, with some weighting for proximity.

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     ferma
    -0.48
    setCancelable
    -0.42
    TypeMap
    -0.41
     desti
    -0.40
    FunctionFlags
    -0.40
     Alas
    -0.40
     mondi
    -0.39
     Lyd
    -0.38
    dach
    -0.38
    Len
    -0.38
    POSITIVE LOGITS
    帖最后由
    0.86
    ImageContext
    0.75
    WebVitals
    0.75
    DockStyle
    0.73
    SupportActionBar
    0.71
     typelib
    0.68
    BufferException
    0.65
     الحره
    0.64
    WriteAttribute
    0.64
     GeoNames
    0.63
    Activations Density 0.599%

    No Known Activations