© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 10370
    Prev
    Next
    INDEX
    Explanations

    jargon related to medical or legal cases

    oai_token-act-pair · gemini-2.0-flash

    Code/legal punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    mybatisplus
    -0.77
    يكب
    -0.71
    Filmografie
    -0.69
    ViewImports
    -0.67
    ContentAsync
    -0.66
    ביוגרפיה
    -0.66
     AppColors
    -0.64
    Життєпис
    -0.63
     disambiguazione
    -0.62
     تانيه
    -0.61
    POSITIVE LOGITS
    '}),
    0.60
    )}}{
    0.59
    ){\
    0.59
    !***
    0.59
    !#
    0.58
    }}_
    0.57
    )#
    0.57
    |}{\
    0.56
    ]^
    0.56
    ]],
    0.56
    Activations Density 29.187%

    No Known Activations