© 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. 5148
    Prev
    Next
    INDEX
    Explanations

    suffixes and prefixes indicating a category or field of study

    oai_token-act-pair · gemini-2.0-flash

    parallelization concepts or methods

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

    Technical academic texts

    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
     EClass
    -0.52
     متعلقه
    -0.47
    tan
    -0.46
     FetchType
    -0.46
     Latimer
    -0.45
    osan
    -0.45
    houding
    -0.44
    COS
    -0.44
     hote
    -0.44
     Herr
    -0.44
    POSITIVE LOGITS
    脚注の使い方
    0.57
    MLLoader
    0.56
     berlaku
    0.56
     esternos
    0.55
    SharedDtor
    0.55
    resave
    0.53
    SequentialGroup
    0.52
    getMenuInflater
    0.50
    IsContent
    0.49
    цездатний
    0.48
    Activations Density 1.889%

    No Known Activations