© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6826
    Prev
    Next
    INDEX
    Explanations

    prepositions or adverbs describing how far away something is

    oai_token-act-pair · gemini-2.0-flash

    all/at

    np_max-act-logits · gemini-2.0-flash
    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
    adpleegd
    -0.94
    Geplaatst
    -0.86
    HtmlAttribute
    -0.85
    httphttps
    -0.78
    ViewFeatures
    -0.78
    memoized
    -0.78
    DoubleQuotes
    -0.77
    rawDesc
    -0.76
    __(/*!
    -0.75
     BoxFit
    -0.73
    POSITIVE LOGITS
     the
    1.63
    the
    0.57
     la
    0.51
    ofthe
    0.47
     pessoais
    0.39
     την
    0.36
     los
    0.36
     automatiques
    0.36
     teratur
    0.35
     ofthe
    0.33
    Activations Density 1.867%

    No Known Activations