© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1841
    Prev
    Next
    INDEX
    Explanations

    punctuation used in code and social media

    oai_token-act-pair · gemini-2.0-flash

    patterns involving quotes or special characters

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

    code and file paths

    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
     pinulongan
    -0.69
    DockStyle
    -0.66
    TargetException
    -0.65
    UnusedPrivate
    -0.59
    @[+][
    -0.59
    AutoresizingMask
    -0.58
     BoxFit
    -0.58
     otomatig
    -0.55
    RectangleBorder
    -0.55
     CreateTagHelper
    -0.54
    POSITIVE LOGITS
    yle
    0.56
    UnitTesting
    0.51
    ಯ
    0.51
    ın
    0.50
    ыгана
    0.50
    YLE
    0.49
    ;->
    0.48
     red
    0.48
     aside
    0.47
    XmlType
    0.46
    Activations Density 0.180%

    No Known Activations