© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6948
    Prev
    Next
    INDEX
    Explanations

    words associated with oral health, saliva, or the tongue

    oai_token-act-pair · gemini-2.0-flash

    Oral health and saliva

    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
     mouth
    -1.66
     Mouth
    -1.54
     mouths
    -1.45
    Mouth
    -1.39
    mouth
    -1.36
     mouthful
    -1.16
    mouthed
    -1.14
     oral
    -1.12
     Oral
    -1.06
    Oral
    -1.03
    POSITIVE LOGITS
    JNIEnv
    0.61
    Diwedd
    0.59
    wpi
    0.57
     CreateTagHelper
    0.56
    SuppressLint
    0.55
    setArguments
    0.54
     harp
    0.52
     sanitarias
    0.51
    principalColumn
    0.51
     Madura
    0.51
    Activations Density 1.805%

    No Known Activations