© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4365
    Prev
    Next
    INDEX
    Explanations

    a variety of technical and descriptive terms that suggest a scientific or analytical context .

    oai_token-act-pair · gemini-2.0-flash

    changes and modifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ValueStyle
    -0.88
     يتيمه
    -0.84
    fjspx
    -0.79
    protoimpl
    -0.73
     الحره
    -0.71
     veloce
    -0.70
    quick
    -0.69
    Quick
    -0.69
     quick
    -0.68
     rapide
    -0.68
    POSITIVE LOGITS
     JTextArea
    0.48
     }).
    0.47
    ropra
    0.45
    softc
    0.44
     hậu
    0.43
    พาะ
    0.40
     Trọng
    0.40
    iomanip
    0.40
    ậc
    0.40
    Elsewhere
    0.40
    Activations Density 25.314%

    No Known Activations