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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 859
    Prev
    Next
    INDEX
    Explanations

    words, dates, and phrases associated with historical events and information

    oai_token-act-pair · gemini-2.0-flash

    Random historical facts

    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
     see
    -3.02
    see
    -2.67
     See
    -2.56
    See
    -2.48
     sees
    -2.45
     seen
    -2.20
     seeing
    -2.16
     SEE
    -2.16
    SEE
    -2.02
    seeing
    -1.88
    POSITIVE LOGITS
     Signalez
    0.63
    ]-->
    0.59
    Портали
    0.58
    httphttps
    0.57
     @"/
    0.52
    invokeLater
    0.51
    rafo
    0.49
    PreferredItem
    0.49
    تقاوى
    0.49
    PerformLayout
    0.49
    Activations Density 7.173%

    No Known Activations