© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3549
    Prev
    Next
    INDEX
    Explanations

    medical terminology - especially words and phrases related to the heart, blood vessels, blood, and cancer malignancy.

    oai_token-act-pair · gemini-2.0-flash

    terms related to cardiology

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

    Medical and biological terms

    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
    DoubleQuotes
    -0.80
    Personendaten
    -0.77
    styleType
    -0.72
     onCreateView
    -0.72
    msgTypes
    -0.71
    addCriterion
    -0.70
    Portály
    -0.68
    oredCriteria
    -0.68
    tagHelperRunner
    -0.67
     <>",
    -0.67
    POSITIVE LOGITS
    log
    0.51
    -
    0.49
    Red
    0.45
    Log
    0.43
    pro
    0.43
    id
    0.42
    count
    0.41
    deepcopy
    0.41
    me
    0.40
    idex
    0.40
    Activations Density 1.040%

    No Known Activations