© 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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 13152
    Prev
    Next
    INDEX
    Explanations

    short sequences of common words

    oai_token-act-pair · gemini-2.0-flash

    all

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     invokingState
    -0.93
    Дереккөздер
    -0.89
     <<<<<<<<<<<<<<
    -0.86
    __*/
    -0.85
    didSet
    -0.76
    ngdoc
    -0.73
    matchCondition
    -0.73
    Portale
    -0.72
    AddTagHelper
    -0.72
     ""],
    -0.71
    POSITIVE LOGITS
     all
    1.47
     All
    1.13
    All
    1.02
    all
    1.02
     ALL
    0.87
     все
    0.78
    ALL
    0.72
     sud
    0.72
     всех
    0.62
     nag
    0.59
    Activations Density 0.554%

    No Known Activations