© 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. 10113
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "see" and synonyms for "find".

    oai_token-act-pair · gemini-2.0-flash

    question-related keywords or phrases

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

    observation

    np_max-act-logits · gemini-2.0-flash

    see

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     judicia
    -0.46
     cherchés
    -0.46
    unal
    -0.44
    ofon
    -0.43
     nhật
    -0.43
     SERIAL
    -0.43
     Towel
    -0.42
     imun
    -0.42
    board
    -0.42
     kanyang
    -0.41
    POSITIVE LOGITS
     how
    0.94
     CreateTagHelper
    0.87
    IUrlHelper
    0.75
     what
    0.75
     why
    0.74
     وتسجيلات
    0.72
     where
    0.70
    tagHelperRunner
    0.68
    CreateModel
    0.68
     BoxDecoration
    0.67
    Activations Density 4.575%

    No Known Activations