© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3453
    Prev
    Next
    INDEX
    Explanations

    the word "wall" occurring in many different contexts

    oai_token-act-pair · gemini-2.0-flash

    wall

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     mass
    -0.57
    <?=$
    -0.57
     "
    -0.55
     type
    -0.54
     likely
    -0.52
     cad
    -0.52
     dvs
    -0.51
     first
    -0.51
     relative
    -0.50
     native
    -0.49
    POSITIVE LOGITS
    fjspx
    0.93
     kasarigan
    0.91
    expandindo
    0.83
     autorytatywna
    0.82
    BeginContext
    0.82
     cherchés
    0.79
    AccessorTable
    0.79
     مرئيه
    0.79
    Rüyada
    0.77
     незавершена
    0.76
    Activations Density 0.413%

    No Known Activations