© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15528
    Prev
    Next
    INDEX
    Explanations

    phrases about families and also phrases about processes

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    NgModule
    -0.76
    coroutines
    -0.76
    eseorang
    -0.75
    CloseOperation
    -0.72
    ]")]
    -0.72
    BeginContext
    -0.68
    nastics
    -0.68
    DotNetBar
    -0.65
    addContainerGap
    -0.65
     SwitchCompat
    -0.65
    POSITIVE LOGITS
     sauter
    0.45
     dietro
    0.42
    RegressionTest
    0.40
     colspan
    0.40
    koliv
    0.39
    :✨
    0.38
    Hochspringen
    0.37
     nhiêu
    0.36
    ینده
    0.36
    <
    0.36
    Activations Density 0.718%

    No Known Activations