© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8944
    Prev
    Next
    INDEX
    Explanations

    words related to taking something and words ending in "all"

    oai_token-act-pair · gemini-2.0-flash

    HTML and Code Snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     uuidv
    -0.52
     пала
    -0.50
    <bos>
    -0.45
     prese
    -0.44
     choice
    -0.42
     pinion
    -0.42
     lui
    -0.41
     الفر
    -0.41
     canna
    -0.41
    Autoritní
    -0.40
    POSITIVE LOGITS
    éviter
    0.80
    addCriterion
    0.68
    ();)
    0.68
     كومونز
    0.67
    CodeAttribute
    0.67
    rrggbb
    0.66
    kegaard
    0.63
    iempos
    0.62
    İstinadlar
    0.62
    empêcher
    0.62
    Activations Density 2.303%

    No Known Activations