© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11046
    Prev
    Next
    INDEX
    Explanations

    java code and the words/characters commonly found within it

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    orteur
    -0.65
    ratulations
    -0.65
    ENOMEM
    -0.63
    kfree
    -0.63
    iterranean
    -0.61
    퀀
    -0.58
    illaume
    -0.58
    ENODEV
    -0.57
    endphp
    -0.57
    amemnon
    -0.57
    POSITIVE LOGITS
    ArrowToggle
    0.49
    Minor
    0.48
     Bead
    0.47
    Bead
    0.44
     ariel
    0.43
    Fay
    0.43
    Tes
    0.42
     bede
    0.42
     "}";
    0.42
    faire
    0.41
    Activations Density 2.513%

    No Known Activations