© 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. 14751
    Prev
    Next
    INDEX
    Explanations

    text describing medical problems, especially allergies and pink eye (conjunctivitis), their symptoms, and potential environmental factors.

    oai_token-act-pair · gemini-2.0-flash

    responses related to allergy symptoms

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

    Skin and eye 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_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
    Amicalement
    -0.78
    sizeCache
    -0.75
     initComponents
    -0.75
    ngdoc
    -0.70
    SourceChecksum
    -0.69
    LookAnd
    -0.68
    FTFY
    -0.68
    存于互联网档案馆
    -0.68
    tvguidetime
    -0.68
    AccessorTable
    -0.68
    POSITIVE LOGITS
     sal
    0.50
    urs
    0.43
     dry
    0.41
     secos
    0.41
     Ir
    0.41
    Ir
    0.41
    류
    0.40
    irs
    0.40
    ec
    0.40
     ",";
    0.40
    Activations Density 1.043%

    No Known Activations