© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6569
    Prev
    Next
    INDEX
    Explanations

    words from a variety of domains, including biology, family, language and food

    oai_token-act-pair · gemini-2.0-flash

    say relative pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    RTEE
    -0.77
    DockStyle
    -0.69
    findpost
    -0.59
    sidemargin
    -0.59
    mentaux
    -0.58
    Leftrightarrow
    -0.57
    انيف
    -0.57
    hoeddwyd
    -0.57
    TextAppearance
    -0.57
    PageContext
    -0.56
    POSITIVE LOGITS
     who
    0.62
    Życiorys
    0.59
     consisting
    0.58
     which
    0.57
    WebServlet
    0.56
     featuring
    0.54
     whose
    0.54
     comprising
    0.53
    DebuggerNonUser
    0.52
     specialising
    0.52
    Activations Density 4.592%

    No Known Activations