© 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. 14574
    Prev
    Next
    INDEX
    Explanations

    terms related to skin conditions and medical treatments

    oai_token-act-pair · gemini-2.0-flash

    medical/research papers

    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
     hold
    -1.72
     holding
    -1.64
     HOLD
    -1.57
    hold
    -1.54
     Hold
    -1.52
    Holding
    -1.52
    holding
    -1.51
    Hold
    -1.50
     Holding
    -1.50
    HOLD
    -1.47
    POSITIVE LOGITS
     LIBR
    0.46
     physical
    0.45
    ört
    0.45
    cester
    0.44
    壤
    0.42
    LabelTagHelper
    0.42
     aqu
    0.41
    cestershire
    0.41
     físicos
    0.40
    داية
    0.39
    Activations Density 2.331%

    No Known Activations