© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12376
    Prev
    Next
    INDEX
    Explanations

    number sequences such as those found in scientific citations

    oai_token-act-pair · gemini-2.0-flash

    eight/8

    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
     Junho
    -0.57
    JsonFormat
    -0.51
     FIFTH
    -0.51
    entieth
    -0.51
     Sixth
    -0.48
     Савезне
    -0.46
     Fifth
    -0.46
    ₅
    -0.46
     vere
    -0.46
    żu
    -0.46
    POSITIVE LOGITS
    8
    0.73
     eighth
    0.65
     Eight
    0.64
     eight
    0.61
    八
    0.59
    Eight
    0.59
     VIII
    0.58
     oito
    0.58
     Eighth
    0.57
    eight
    0.56
    Activations Density 3.790%

    No Known Activations