© 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. 4049
    Prev
    Next
    INDEX
    Explanations

    measurements from experimental procedures or scientific values

    oai_token-act-pair · 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
     AssemblyCulture
    -1.14
     ten
    -0.89
     Ten
    -0.87
    Ten
    -0.86
    ten
    -0.77
     TEN
    -0.76
    GEBURTSDATUM
    -0.74
    featureID
    -0.72
     CreateTagHelper
    -0.72
     Signalez
    -0.71
    POSITIVE LOGITS
    \{\\
    0.50
    7
    0.49
    नीय
    0.46
    regate
    0.45
    9
    0.45
    ynch
    0.45
    umpe
    0.44
    ẻo
    0.42
    "]/
    0.40
    катерина
    0.40
    Activations Density 2.717%

    No Known Activations