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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1600
    Prev
    Next
    INDEX
    Explanations

    information about numbers, time, and memory

    oai_token-act-pair · gemini-2.0-flash

    0

    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
     Efq
    -0.87
     Monfieur
    -0.80
     Theſe
    -0.80
     ſeveral
    -0.75
     purpoſe
    -0.75
     ſmall
    -0.74
     سكانية
    -0.72
     myſelf
    -0.72
     himſelf
    -0.72
     ſhe
    -0.72
    POSITIVE LOGITS
    l
    0.57
    })}
    0.53
    ).}
    0.52
    /"
    0.52
    })}$
    0.51
    c
    0.50
    m
    0.50
    b
    0.49
    /}.
    0.49
    ))}
    0.48
    Activations Density 5.569%

    No Known Activations