© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11712
    Prev
    Next
    INDEX
    Explanations

    technical writing describing how things are made or done

    oai_token-act-pair · gemini-2.0-flash

    explanations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     stället
    -0.65
     noires
    -0.63
     financière
    -0.63
     brancas
    -0.61
     étrangère
    -0.61
    AndEndTag
    -0.60
     vermelhas
    -0.60
     personnelle
    -0.56
     pasada
    -0.56
     egne
    -0.56
    POSITIVE LOGITS
    Personensuche
    0.81
    AccessorTable
    0.65
     betweenstory
    0.61
    HttpPut
    0.59
    EndGlobalSection
    0.58
    #+#
    0.57
     INSEE
    0.56
    ⓧ
    0.56
     localVar
    0.54
    qrstuvwxyz
    0.54
    Activations Density 7.888%

    No Known Activations