© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15050
    Prev
    Next
    INDEX
    Explanations

    terms related to software or application development or use, or financial matters

    oai_token-act-pair · gemini-2.0-flash

    Business contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     ſeveral
    -0.95
     myſelf
    -0.93
     himſelf
    -0.90
     Theſe
    -0.90
     iſt
    -0.88
     Beſ
    -0.86
     themſelves
    -0.84
     pleaſure
    -0.83
     chofe
    -0.82
     Anſ
    -0.81
    POSITIVE LOGITS
     iprot
    0.56
     upd
    0.54
    <bos>
    0.51
     SwitchCompat
    0.49
     tym
    0.48
     &
    0.47
     пол
    0.45
    tisgarh
    0.44
     pula
    0.43
    (__('
    0.43
    Activations Density 3.115%

    No Known Activations