Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6350
    Prev
    Next
    INDEX
    Explanations

    beginning quotations

    oai_token-act-pair · gemini-2.0-flash

    quotation marks

    np_token-act-pair-logits · gpt-4o-mini

    quotation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     “
    -1.61
     "
    -1.60
     ”
    -0.98
     
    -0.94
     ""
    -0.93
     „
    -0.92
     ("
    -0.89
     tr
    -0.87
     (“
    -0.87
     "/
    -0.86
    POSITIVE LOGITS
     Shakspeare
    1.77
     Majefty
    1.70
     itſelf
    1.69
     myſelf
    1.61
     Jefus
    1.59
     Monfieur
    1.59
     Diſ
    1.52
     themſelves
    1.50
     Efq
    1.48
     Anſ
    1.46
    Activations Density 0.578%

    No Known Activations