© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5235
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs like 'be' and 'can' that can be used in questions

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     doing
    -2.47
     Doing
    -2.34
    Doing
    -2.33
     do
    -2.33
    doing
    -2.20
    do
    -2.02
     Do
    -1.96
     DOING
    -1.96
    Do
    -1.90
     doin
    -1.82
    POSITIVE LOGITS
    цездатний
    0.68
     وتسجيلات
    0.61
    BeginContext
    0.61
    цезда
    0.61
     Offisielt
    0.59
     ComVisible
    0.59
    transQ
    0.57
     transférez
    0.57
     surla
    0.55
    ROIT
    0.53
    Activations Density 2.046%

    No Known Activations