© 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. 10862
    Prev
    Next
    INDEX
    Explanations

    a broad variety of terms used in distinct contexts like coding, parenthood, and cooking.

    oai_token-act-pair · gemini-2.0-flash

    something is wrong

    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
     متعلقه
    -0.78
     kasarigan
    -0.68
     truncation
    -0.65
    ecake
    -0.63
     Amad
    -0.62
    atae
    -0.61
     Damas
    -0.61
    nolia
    -0.61
     Freeway
    -0.60
    acuation
    -0.60
    POSITIVE LOGITS
     wrong
    0.59
    UnusedPrivate
    0.58
     snippetHide
    0.57
     InputDecoration
    0.52
     differently
    0.52
    AnchorStyles
    0.50
     hot
    0.49
    ConstraintMaker
    0.48
    BeginInit
    0.47
     perfectly
    0.46
    Activations Density 3.809%

    No Known Activations