© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9209
    Prev
    Next
    INDEX
    Explanations

    words/phrases relating to something working or body movements happening.

    oai_token-act-pair · gemini-2.0-flash

    like

    np_max-act-logits · gemini-2.0-flash

    say "adverb"

    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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    BufferException
    -0.69
    تفصیلات
    -0.65
    XmlAccessType
    -0.61
    cshtml
    -0.60
    ureusement
    -0.60
     Paglinawan
    -0.59
    Бахар
    -0.54
    doria
    -0.54
     محفوظة
    -0.54
     AssemblyProduct
    -0.53
    POSITIVE LOGITS
     like
    3.14
     Like
    2.38
    Like
    2.34
     LIKE
    2.17
    like
    2.16
    LIKE
    1.73
     seperti
    1.73
     như
    1.48
     zoals
    1.40
     Seperti
    1.40
    Activations Density 3.000%

    No Known Activations