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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3626
    Prev
    Next
    INDEX
    Explanations

    legal statutes and acts

    oai_token-act-pair · gemini-2.0-flash

    legal statutes and acts

    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
    poder
    -0.50
    esgue
    -0.49
    UMIN
    -0.48
    Parameterized
    -0.48
    onenumber
    -0.48
    TextWatcher
    -0.48
    τί
    -0.47
    vav
    -0.47
    +#+
    -0.47
     الحره
    -0.47
    POSITIVE LOGITS
     out
    0.56
    out
    0.54
    Билгалдахарш
    0.53
    GraphicsUnit
    0.52
    Out
    0.52
     Out
    0.52
    Capítulo
    0.52
    InjectAttribute
    0.50
    RegressionTest
    0.49
    __':
    0.47
    Activations Density 7.708%

    No Known Activations