© 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. 16361
    Prev
    Next
    INDEX
    Explanations

    words and phrases from archeology

    oai_token-act-pair · gemini-2.0-flash

    geology and landscapes

    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
    Witam
    -0.45
     kanyang
    -0.43
    moiselle
    -0.42
    TBA
    -0.42
    horabuena
    -0.42
    crí
    -0.41
    Istorija
    -0.40
    GetProperty
    -0.40
    endphp
    -0.40
    ējās
    -0.40
    POSITIVE LOGITS
    ########.
    0.88
     propOrder
    0.87
    setVerticalGroup
    0.82
    complexType
    0.71
     виправивши
    0.69
    featureID
    0.64
    tagHelperRunner
    0.64
    EndContext
    0.61
    UrlResolution
    0.60
    richTextPanel
    0.60
    Activations Density 3.250%

    No Known Activations