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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11196
    Prev
    Next
    INDEX
    Explanations

    descriptions of athlete's height, weight and statistics

    oai_token-act-pair · gemini-2.0-flash

    words and terms related to movement or proximity

    np_token-act-pair-logits · gpt-4o-mini

    heights of people

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    jsonwebtoken
    -0.71
     Waray
    -0.71
    脚注の使い方
    -0.69
    ]")]
    -0.67
    ंदीखरीदारी
    -0.66
    তথ্যসূত্র
    -0.66
    MigrationBuilder
    -0.65
    LookAnd
    -0.62
     defaultstate
    -0.60
     ProtoMessage
    -0.59
    POSITIVE LOGITS
    windowFixed
    0.58
     around
    0.57
     Around
    0.52
    Around
    0.52
    dır
    0.49
     mulig
    0.49
    around
    0.49
    rededor
    0.47
     möj
    0.47
     esclu
    0.46
    Activations Density 0.647%

    No Known Activations