© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13330
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce a list or small number of examples

    oai_token-act-pair · gemini-2.0-flash

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     few
    -1.70
     Few
    -1.54
    few
    -1.52
    Few
    -1.51
     FEW
    -1.27
     paar
    -1.09
     quelques
    -1.09
     poucos
    -0.98
     Quelques
    -0.96
     pocos
    -0.95
    POSITIVE LOGITS
     a
    1.89
    a
    1.15
    A
    0.78
     A
    0.73
    getA
    0.70
     @}
    0.67
    ａ
    0.65
    ագրություններ
    0.61
    脚注の使い方
    0.60
    aktery
    0.60
    Activations Density 5.882%

    No Known Activations