© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6549
    Prev
    Next
    INDEX
    Explanations

    code related to UI buttons and event handling

    oai_token-act-pair · gemini-2.0-flash

    numeric representations and variants of the number six

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

    Number 6

    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
    ViewFeatures
    -0.69
    enderror
    -0.63
    featureID
    -0.62
     ISNI
    -0.57
     Three
    -0.56
     distanciation
    -0.55
     пожалуйста
    -0.54
     tangerang
    -0.53
     three
    -0.53
     THREE
    -0.52
    POSITIVE LOGITS
    6
    0.75
     sixth
    0.64
     six
    0.60
     Six
    0.54
    חה
    0.54
    7
    0.52
    六
    0.51
    ⑥
    0.50
    第六
    0.50
    Sixth
    0.49
    Activations Density 1.753%

    No Known Activations