© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12875
    Prev
    Next
    INDEX
    Explanations

    the conversational phrase "you know what I mean" or "you get the picture"

    oai_token-act-pair · gemini-2.0-flash

    conversational, suggestive imagery

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ContentAsync
    -0.77
    <bos>
    -0.75
    NameInMap
    -0.69
     AssemblyCulture
    -0.69
    TableAdapter
    -0.65
     Roskov
    -0.63
    findpost
    -0.63
    UnsafeEnabled
    -0.63
    parsedMessage
    -0.58
    /*---
    -0.57
    POSITIVE LOGITS
     ſen
    0.69
     purpoſe
    0.66
     perſon
    0.66
     beſt
    0.65
     greateſt
    0.63
     neceſſ
    0.62
     reaſon
    0.62
     pleaſure
    0.59
    fromnode
    0.59
     ſame
    0.58
    Activations Density 2.835%

    No Known Activations