© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12549
    Prev
    Next
    INDEX
    Explanations

    phrases about the lack of other options or requirements

    oai_token-act-pair · gemini-2.0-flash

    choice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     '\\;'
    -0.74
     ModelRenderer
    -0.67
    sendRedirect
    -0.61
     bpy
    -0.61
    principalColumn
    -0.60
     Numerade
    -0.60
    ]]
    -0.58
    atified
    -0.58
    WebServlet
    -0.56
     HttpNotFound
    -0.56
    POSITIVE LOGITS
     Necessity
    0.64
     inevitable
    0.62
     unavoidable
    0.56
    psack
    0.51
     inescapable
    0.51
     inevit
    0.50
     necessity
    0.50
    限
    0.50
     constraints
    0.49
     Constraint
    0.48
    Activations Density 0.771%

    No Known Activations