© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15791
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to medical skin conditions and treatments

    oai_token-act-pair · gemini-2.0-flash

    skin conditions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    oa̍t
    -0.66
    Décès
    -0.63
     AssemblyCulture
    -0.60
     OFDb
    -0.56
    loài
    -0.56
     Lively
    -0.56
    StoryboardSegue
    -0.55
    msgTypes
    -0.54
    tagHelperRunner
    -0.52
     ProtoMessage
    -0.52
    POSITIVE LOGITS
    yarnpkg
    0.56
     ecc
    0.49
    örös
    0.43
    ChromeDriver
    0.43
    andum
    0.42
    Према
    0.42
    oubliez
    0.42
    orf
    0.41
    :+:
    0.41
    Bout
    0.41
    Activations Density 1.514%

    No Known Activations