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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7327
    Prev
    Next
    INDEX
    Explanations

    the word "speech"

    oai_token-act-pair · gemini-2.0-flash

    speech

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Theſe
    -0.71
    interopRequire
    -0.69
     soñ
    -0.66
    wakili
    -0.64
    LECTIONS
    -0.64
     Pollut
    -0.63
     endeavouring
    -0.63
    ticons
    -0.63
     réguli
    -0.63
    ViewImports
    -0.62
    POSITIVE LOGITS
    ActionMode
    0.68
     work
    0.55
    OGND
    0.54
     ModelExpression
    0.54
    Tracce
    0.53
     وصلة
    0.49
    おお
    0.49
     use
    0.48
    InteropServices
    0.48
    انيف
    0.48
    Activations Density 0.280%

    No Known Activations