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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 2288
    Prev
    Next
    INDEX
    Explanations

    words in a sales pitch

    oai_token-act-pair · gemini-2.0-flash

    Prices and costs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    frastructure
    -0.49
    <bos>
    -0.47
    emples
    -0.43
     discernment
    -0.42
    rī
    -0.42
     correlations
    -0.42
     distortions
    -0.41
    ἔ
    -0.40
    وصلات
    -0.40
    logeny
    -0.39
    POSITIVE LOGITS
     فريبيس
    0.79
    ftagPool
    0.74
    出版年
    0.74
     AssemblyCulture
    0.69
    SequentialGroup
    0.63
    6
    0.63
    Gön
    0.63
    AnimationsModule
    0.62
    5
    0.61
    SpringBootTest
    0.60
    Activations Density 16.781%

    No Known Activations