© 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. 12558
    Prev
    Next
    INDEX
    Explanations

    URL domain names

    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
    ⓧ
    -0.79
    apimachinery
    -0.65
    IVEREF
    -0.64
    GEBURTSDATUM
    -0.61
    OrBuilder
    -0.60
    daction
    -0.59
    RegistryLite
    -0.57
    ectoria
    -0.57
    uckland
    -0.57
    XmlAccessorType
    -0.57
    POSITIVE LOGITS
     coû
    0.65
    com
    0.60
    come
    0.60
     come
    0.55
    كوم
    0.52
    ppure
    0.52
    enumi
    0.51
    Come
    0.51
    הערות
    0.51
     EconPapers
    0.51
    Activations Density 0.282%

    No Known Activations