© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12485
    Prev
    Next
    INDEX
    Explanations

    words and phrases describing certifications or qualifications related to massage therapy

    oai_token-act-pair · gemini-2.0-flash

    terms related to rehabilitation or therapy

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

    rehabilitation

    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
    AnchorStyles
    -0.69
    isContained
    -0.64
     мәкал
    -0.63
    yntaxException
    -0.59
    Портал
    -0.58
    ectoria
    -0.56
    AccessorTable
    -0.54
    OGND
    -0.54
    IVersion
    -0.53
    الحياه
    -0.52
    POSITIVE LOGITS
     فريبيس
    0.56
     EconPapers
    0.54
    bewerken
    0.52
     rehabilitation
    0.48
     Rehabilitation
    0.48
     rehab
    0.47
    hood
    0.47
     Ortho
    0.46
     ker
    0.46
     Rehab
    0.46
    Activations Density 1.116%

    No Known Activations