© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3969
    Prev
    Next
    INDEX
    Explanations

    place names and addresses in the UK

    oai_token-act-pair · gemini-2.0-flash

    technical text snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    はじめに
    -0.49
    attributes
    -0.49
     répondit
    -0.47
    ometrics
    -0.47
     impinge
    -0.47
    Keterangan
    -0.46
     Bingham
    -0.46
    Footnotes
    -0.46
     fizer
    -0.45
    бият
    -0.45
    POSITIVE LOGITS
     snippetHide
    0.70
     فريبيس
    0.68
     jadx
    0.61
     насељу
    0.56
    IntoConstraints
    0.54
    BeginInit
    0.53
    addPreferredGap
    0.52
     lenker
    0.52
    ValueStyle
    0.52
    ServletException
    0.51
    Activations Density 0.848%

    No Known Activations