© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2951
    Prev
    Next
    INDEX
    Explanations

    HTML code, specifically the href attribute and toggle functions

    oai_token-act-pair · gemini-2.0-flash

    href

    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
     href
    -1.28
    #+#
    -0.89
     كومونز
    -0.82
    href
    -0.82
    +:+
    -0.72
     GenerationType
    -0.67
    
    -0.66
    :+:
    -0.66
    endphp
    -0.64
     stickied
    -0.64
    POSITIVE LOGITS
    awtextra
    0.50
    i
    0.49
     beginnetje
    0.47
     Gottes
    0.47
     الرخصة
    0.44
    kony
    0.44
     tablas
    0.41
    örande
    0.41
     clearColor
    0.40
    хьтан
    0.40
    Activations Density 0.477%

    No Known Activations