© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5376
    Prev
    Next
    INDEX
    Explanations

    whitespace at the start of a line

    oai_token-act-pair · gemini-2.0-flash

    programming terms or elements

    np_token-act-pair-logits · gpt-4o-mini

    code and numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    IVEREF
    -0.60
    liquer
    -0.57
     kwam
    -0.56
    XmlIgnore
    -0.53
     Himo
    -0.53
    UrlResolution
    -0.52
    numeros
    -0.52
     olvides
    -0.51
     vecka
    -0.51
    bindung
    -0.51
    POSITIVE LOGITS
     propOrder
    0.71
    SequentialGroup
    0.58
    PreferredItem
    0.56
    IsMutable
    0.52
    DataAnnotations
    0.51
    ModelBuilder
    0.50
    MethodManager
    0.49
    fromCharCode
    0.48
    tagHelperRunner
    0.46
    поле
    0.45
    Activations Density 0.310%

    No Known Activations