© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14557
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to limbs and surgery

    oai_token-act-pair · gemini-2.0-flash

    terms related to limb procedures and anatomy

    np_token-act-pair-logits · gpt-4o-mini

    say body parts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     finger
    -0.88
     knuckles
    -0.88
     thumb
    -0.82
     Finger
    -0.82
     knees
    -0.79
    finger
    -0.78
     fingers
    -0.75
    Finger
    -0.74
     palm
    -0.73
     fingertips
    -0.72
    POSITIVE LOGITS
    adpleegd
    0.60
    HtmlAttribute
    0.59
     VIDEOTAPE
    0.54
    arXiv
    0.54
    createCanvas
    0.54
     limb
    0.49
    findById
    0.48
    addComponent
    0.47
    HasForeignKey
    0.47
    程
    0.46
    Activations Density 1.390%

    No Known Activations