© 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. 6582
    Prev
    Next
    INDEX
    Explanations

    words which come before or after the word "under"

    oai_token-act-pair · gemini-2.0-flash

    the

    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
     under
    -3.13
    Under
    -3.02
    under
    -2.94
     Under
    -2.92
     UNDER
    -2.67
    UNDER
    -2.50
     unter
    -2.19
     bajo
    -2.13
     sotto
    -2.08
     sous
    -2.06
    POSITIVE LOGITS
     betweenstory
    0.93
    PasswordEncoder
    0.79
    saraba
    0.78
    PyTuple
    0.59
    Portale
    0.58
    AutoresizingMask
    0.58
    olingo
    0.58
    setViewportView
    0.57
    StackNavigator
    0.57
    protoimpl
    0.57
    Activations Density 5.530%

    No Known Activations