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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4920
    Prev
    Next
    INDEX
    Explanations

    periods, particularly those that start or end a sentence or abbreviation

    oai_token-act-pair · gemini-2.0-flash

    Period symbol

    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
     
    -3.06
    <eos>
    -2.47
    ↵↵
    -2.44
     "
    -2.16
     “
    -2.09
     (
    -2.03
     '
    -1.95
     I
    -1.95
    ↵
    -1.91
     A
    -1.91
    POSITIVE LOGITS
     myſelf
    4.69
     itſelf
    4.63
     Efq
    4.63
     Monfieur
    4.38
     Majefty
    4.28
     pleaſure
    4.22
     purpoſe
    4.19
     Jefus
    4.16
     themſelves
    4.09
     Anſ
    4.09
    Activations Density 3.491%

    No Known Activations