© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15584
    Prev
    Next
    INDEX
    Explanations

    end-of-sentence punctuation preceded by certain common words such as prepositions, verbs, pronouns, etc

    oai_token-act-pair · gemini-2.0-flash

    quoted speech

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     čierna
    -0.54
     meanwhile
    -0.52
    ρίες
    -0.46
     sumpay
    -0.45
    ])):
    -0.44
     száll
    -0.44
    Alike
    -0.44
    Välislingid
    -0.43
    soever
    -0.42
    Напомним
    -0.42
    POSITIVE LOGITS
    uxxxx
    0.73
    webElementXpaths
    0.65
    InitVars
    0.62
    WriteBarrier
    0.58
    EndGlobalSection
    0.57
    saraba
    0.57
     nogal
    0.57
    HtmlAttribute
    0.56
    principalTable
    0.55
    (!__
    0.54
    Activations Density 0.745%

    No Known Activations