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. 15-GEMMASCOPE-TRANSCODER-16K
    4. 16363
    Prev
    Next
    INDEX
    Explanations

    Java code

    oai_token-act-pair · gemini-2.0-flash

    CACHE

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_15/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
     ddelweddau
    -0.95
    ThemeOverlay
    -0.84
     désolés
    -0.74
     صوتيه
    -0.69
    олові
    -0.65
    rungsseite
    -0.64
     betweenstory
    -0.61
    كويكب
    -0.60
    PARATUS
    -0.59
    Controllo
    -0.57
    POSITIVE LOGITS
     Pristupljeno
    0.52
    WaitGroup
    0.51
    ICALS
    0.49
    ształ
    0.47
     volna
    0.43
    ague
    0.42
    PendingIntent
    0.40
    whit
    0.40
     inplace
    0.40
    ิต
    0.40
    Activations Density 0.383%

    No Known Activations