© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5655
    Prev
    Next
    INDEX
    Explanations

    code and code syntax

    oai_token-act-pair · gemini-2.0-flash

    Code and data structures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     newBuilder
    -0.62
    #+#
    -0.61
    XmlAccessType
    -0.57
    sizeCache
    -0.57
    gameserver
    -0.54
    Filmografie
    -0.51
    ExtendWith
    -0.51
    IContainer
    -0.50
    EVAL
    -0.50
    Хьажоргаш
    -0.49
    POSITIVE LOGITS
    GEBURTSDATUM
    0.60
    extAlignment
    0.60
     otomatig
    0.58
    uxxxx
    0.58
    หน้านี้
    0.56
    ScopeManager
    0.53
    bibinfo
    0.52
     оригіналу
    0.51
     समीक्षाएं
    0.49
     &___
    0.47
    Activations Density 2.322%

    No Known Activations