© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9355
    Prev
    Next
    INDEX
    Explanations

    short sequences of capitalized words

    oai_token-act-pair · gemini-2.0-flash

    Article/legal text

    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
     myſelf
    -0.94
     itſelf
    -0.89
     houſe
    -0.88
     themſelves
    -0.86
     himſelf
    -0.85
    ſelves
    -0.82
     ſtre
    -0.81
     ſtate
    -0.81
     purpoſe
    -0.81
     becauſe
    -0.81
    POSITIVE LOGITS
    one
    0.45
     jambes
    0.44
    ote
    0.41
    oy
    0.41
    og
    0.40
    ms
    0.40
    enn
    0.40
    ny
    0.39
    ik
    0.39
    em
    0.39
    Activations Density 3.457%

    No Known Activations