© 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. 4165
    Prev
    Next
    INDEX
    Explanations

    abstract code syntax

    oai_token-act-pair · gemini-2.0-flash

    code 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
     Efq
    -0.91
     Normdatei
    -0.90
     Jefus
    -0.90
    AndEndTag
    -0.89
    neſs
    -0.89
    RegressionTest
    -0.89
     يتيمه
    -0.85
     itſelf
    -0.84
    CppMethod
    -0.84
    SBATCH
    -0.82
    POSITIVE LOGITS
    <
    0.55
    sh
    0.54
    for
    0.50
    Sh
    0.50
    (
    0.50
    to
    0.49
    素
    0.48
     Sh
    0.47
    막
    0.46
    <em>
    0.46
    Activations Density 11.834%

    No Known Activations