© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1838
    Prev
    Next
    INDEX
    Explanations

    periods at the end of sentences with some additional sensitivity historical or fantasy fiction

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     intptr
    -0.63
    endphp
    -0.57
    matchCondition
    -0.57
    ligente
    -0.53
     المعيارى
    -0.52
    énégal
    -0.52
    tagHelperRunner
    -0.52
    — 
    -0.51
    ंदीखरीदारी
    -0.48
    enderror
    -0.48
    POSITIVE LOGITS
    <bos>
    0.56
     برانيه
    0.56
     مرئيه
    0.55
    oa̍t
    0.53
     للاسماء
    0.50
    thâu
    0.49
    SPATH
    0.48
     Angleterre
    0.47
    GroupName
    0.46
     مواليد
    0.46
    Activations Density 1.507%

    No Known Activations