© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8410
    Prev
    Next
    INDEX
    Explanations

    words that indicate a logical deduction or conclusion is being made

    oai_token-act-pair · gemini-2.0-flash

    therefore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    tvguidetime
    -1.06
     Monfieur
    -1.06
     Efq
    -1.00
     Diſ
    -0.98
     Jefus
    -0.94
     Theſe
    -0.93
     Anſ
    -0.91
     Reſ
    -0.91
     ainfi
    -0.91
     iſt
    -0.89
    POSITIVE LOGITS
    <bos>
    0.49
    Einzelnachweise
    0.47
    Rè
    0.47
    Билгалдахарш
    0.47
     optimally
    0.46
    Hentet
    0.45
     licence
    0.44
    isable
    0.44
     spoilt
    0.44
     !
    0.43
    Activations Density 2.935%

    No Known Activations