© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6428
    Prev
    Next
    INDEX
    Explanations

    speech with people in positions of power asking to be forgiven, and descriptions of protests and religious ceremonies

    oai_token-act-pair · gemini-2.0-flash

    begging

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    RegistryLite
    -0.59
    liceerd
    -0.59
    apimachinery
    -0.58
    ]();
    -0.57
    AutoField
    -0.55
    OGND
    -0.54
    
    -0.52
    inerja
    -0.52
    findpost
    -0.52
    utches
    -0.52
    POSITIVE LOGITS
    <bos>
    0.53
     CreateTagHelper
    0.49
     ask
    0.49
     thanking
    0.47
    BSITE
    0.47
    WindowConstants
    0.46
    ună
    0.44
     continuity
    0.44
     help
    0.44
     inform
    0.43
    Activations Density 2.156%

    No Known Activations