© 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. 14407
    Prev
    Next
    INDEX
    Explanations

    pronouns and related auxiliary verbs

    oai_token-act-pair · gemini-2.0-flash

    personal experiences

    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
    tedly
    -0.53
     meanwhile
    -0.47
    CompleteListener
    -0.46
    存于互联网档案馆
    -0.46
    chets
    -0.45
     rendement
    -0.44
    setNome
    -0.43
    MessageOf
    -0.43
    gefü
    -0.43
    uests
    -0.43
    POSITIVE LOGITS
     estekak
    0.83
    TagMode
    0.68
    tamol
    0.64
    <>();
    0.63
    født
    0.57
    "])
    0.56
     mxArray
    0.56
    peño
    0.55
    mobileqq
    0.54
    AddHtmlAttribute
    0.53
    Activations Density 1.678%

    No Known Activations