© 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. 5620
    Prev
    Next
    INDEX
    Explanations

    references to Microsoft products and technologies

    oai_token-act-pair · gemini-2.0-flash

    Windows

    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
     Esau
    -0.63
     floss
    -0.57
     للاسماء
    -0.56
     végétale
    -0.56
    ้อมูล
    -0.56
     utafitiHapana
    -0.56
    Rohy
    -0.54
     arcu
    -0.53
     GTI
    -0.53
     mariée
    -0.53
    POSITIVE LOGITS
     defaultstate
    0.60
    Jeografia
    0.59
    ūnas
    0.52
     محفوظة
    0.50
     &___
    0.49
    jspx
    0.46
     Talley
    0.46
    ISupport
    0.46
    таратура
    0.46
    MessageDigest
    0.45
    Activations Density 0.543%

    No Known Activations