© 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. 6458
    Prev
    Next
    INDEX
    Explanations

    steps in a scientific procedure

    oai_token-act-pair · gemini-2.0-flash

    Laboratory/chemical processes

    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
    OGND
    -0.82
    Gön
    -0.78
    WithIOException
    -0.72
    DOCTYPE
    -0.71
    ResponseWriter
    -0.71
     Waray
    -0.70
    kháu
    -0.70
    mapStateToProps
    -0.69
    KommentareTeilen
    -0.69
    ValueStyle
    -0.69
    POSITIVE LOGITS
    valt
    0.40
    legg
    0.39
     True
    0.39
     N
    0.39
     falling
    0.39
     leg
    0.39
    chuhe
    0.38
     fall
    0.37
     fell
    0.37
     auto
    0.37
    Activations Density 2.266%

    No Known Activations