© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14226
    Prev
    Next
    INDEX
    Explanations

    phrases containing "you" or "we" and some form of "look".

    oai_token-act-pair · gemini-2.0-flash

    seeking something

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Wikiped
    -0.47
     craters
    -0.46
     asupra
    -0.46
     furrows
    -0.46
     jät
    -0.46
     chofe
    -0.45
     Majefty
    -0.45
     Monfieur
    -0.44
     predeceased
    -0.44
     crater
    -0.44
    POSITIVE LOGITS
    AnchorStyles
    0.78
    __))
    0.72
    存于互联网档案馆
    0.71
    addContainerGap
    0.67
    EndContext
    0.66
    findpost
    0.65
     autorytatywna
    0.64
    PyExc
    0.64
    QMetaType
    0.63
    steria
    0.61
    Activations Density 0.283%

    No Known Activations