Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14647
    Prev
    Next
    INDEX
    Explanations

    the word "club" and related words like "league" and "ball".

    oai_token-act-pair · gemini-2.0-flash

    club

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    DockStyle
    -0.84
    TagMode
    -0.71
    rungsseite
    -0.69
     ***!
    -0.69
    BASEPATH
    -0.65
    webElementXpaths
    -0.62
    VideoCapture
    -0.62
     تعدى
    -0.62
    hoeddwyd
    -0.61
    Personendaten
    -0.59
    POSITIVE LOGITS
    Geplaatst
    0.53
    rooms
    0.50
     sosi
    0.46
     mosso
    0.45
     CreateTagHelper
    0.45
    featureID
    0.45
     meurt
    0.45
     scel
    0.45
     RECOMMENDATIONS
    0.44
     extrait
    0.44
    Activations Density 1.401%

    No Known Activations