© 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. 15914
    Prev
    Next
    INDEX
    Explanations

    temporal references, including dates, times, and seasons, as well as some prepositions

    oai_token-act-pair · gemini-2.0-flash

    the/at

    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
     itſelf
    -0.88
     محفوظة
    -0.86
     ſeveral
    -0.85
    WriteTagHelper
    -0.82
     myſelf
    -0.79
    featureID
    -0.79
     Theſe
    -0.77
     wireType
    -0.76
     againſt
    -0.74
     raiſ
    -0.73
    POSITIVE LOGITS
     first
    0.59
     at
    0.53
     height
    0.51
     break
    0.48
     Ram
    0.47
     Höhe
    0.47
    onset
    0.47
     be
    0.46
     onset
    0.46
    retum
    0.46
    Activations Density 0.629%

    No Known Activations