© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8316
    Prev
    Next
    INDEX
    Explanations

    parts of code that include underscores

    oai_token-act-pair · gemini-2.0-flash

    early modern English vocabulary or archaic terms

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

    underscore

    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
    ,
    -0.85
     N
    -0.77
     M
    -0.76
     H
    -0.75
     A
    -0.73
     (
    -0.73
     S
    -0.73
     
    -0.71
     Q
    -0.71
     I
    -0.70
    POSITIVE LOGITS
     itſelf
    1.34
     Majefty
    1.23
     pleaſure
    1.22
    ſelves
    1.22
     ſta
    1.19
     purpoſe
    1.17
     raiſ
    1.16
     myſelf
    1.15
     ་་
    1.13
     greateſt
    1.13
    Activations Density 1.836%

    No Known Activations