© 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. 3737
    Prev
    Next
    INDEX
    Explanations

    personal anecdotes from blog posts, possibly related to weddings or personal experiences

    oai_token-act-pair · gemini-2.0-flash

    Informal online conversation

    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
     >=",
    -0.64
    inghouse
    -0.60
    ^(@)
    -0.59
    AccessorTable
    -0.58
    IndentedString
    -0.57
    secuencias
    -0.57
     مشين
    -0.56
    ślę
    -0.55
    makeatother
    -0.55
     Commencez
    -0.54
    POSITIVE LOGITS
    AndEndTag
    0.64
    <bos>
    0.55
    DeleteBehavior
    0.53
     الاطلاع
    0.52
     snippetHide
    0.51
    joi
    0.48
     rega
    0.48
    localScale
    0.47
    ’
    0.47
    po
    0.46
    Activations Density 2.418%

    No Known Activations