© 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. 7727
    Prev
    Next
    INDEX
    Explanations

    mentions of vitamins and related nutritional elements, often including dosages or chemical formulas

    oai_token-act-pair · gemini-2.0-flash

    vitamin-related terms

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

    vitamin

    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
    rawdę
    -0.51
     Mound
    -0.43
    []{"
    -0.39
    ఔ
    -0.39
     trail
    -0.38
    wia
    -0.38
    bones
    -0.38
    டு
    -0.38
     behavior
    -0.37
     Aye
    -0.37
    POSITIVE LOGITS
    tvguidetime
    0.84
    findpost
    0.79
    (!__
    0.69
     noDo
    0.65
     ویکی‌پدیای
    0.64
     déput
    0.62
     ainfi
    0.61
     ModelExpression
    0.61
     chodzi
    0.60
    SequentialGroup
    0.60
    Activations Density 1.328%

    No Known Activations