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. 14785
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the shape and use of land and construction.

    oai_token-act-pair · gemini-2.0-flash

    ground and soil

    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
     lenker
    -0.57
    publicain
    -0.46
    AutoScaleMode
    -0.46
    HandlerContext
    -0.46
    ⓘ
    -0.44
     expédié
    -0.44
    jago
    -0.43
    miral
    -0.43
    مراجع
    -0.42
     становника
    -0.42
    POSITIVE LOGITS
     ground
    2.03
    ground
    1.81
    Ground
    1.71
     Ground
    1.70
     GROUND
    1.63
     soil
    1.62
    GROUND
    1.52
     earth
    1.46
    soil
    1.37
     Soil
    1.34
    Activations Density 1.224%

    No Known Activations