© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5428
    Prev
    Next
    INDEX
    Explanations

    the prefix "pri", likely related to "private" or "primary" in different contexts

    oai_token-act-pair · gemini-2.0-flash

    privity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    THISDAY
    -0.60
    tagHelperRunner
    -0.57
    DNEY
    -0.56
     setObject
    -0.56
    QString
    -0.53
     course
    -0.53
     OkHttpClient
    -0.52
    SequentialGroup
    -0.52
    BufferedWriter
    -0.51
    tableFuture
    -0.51
    POSITIVE LOGITS
    Portale
    0.53
    vode
    0.52
    estimators
    0.51
    */),
    0.48
    fromnode
    0.47
    وفاته
    0.46
     Italijanski
    0.46
     concurso
    0.45
     콘텐츠
    0.45
     promoção
    0.45
    Activations Density 0.328%

    No Known Activations