© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10736
    Prev
    Next
    INDEX
    Explanations

    verbs being used

    oai_token-act-pair · gemini-2.0-flash

    describes changes/states

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    ŚCI
    -0.53
    로드
    -0.51
     syke
    -0.49
     Tigre
    -0.48
     africaine
    -0.47
     sanitaires
    -0.47
     ativa
    -0.46
     africains
    -0.46
     ordinaire
    -0.46
     sauvages
    -0.46
    POSITIVE LOGITS
    abestanden
    0.81
    oredCriteria
    0.79
     AssemblyCompany
    0.79
    SequentialGroup
    0.75
     مشين
    0.73
    SourceChecksum
    0.73
     Савезне
    0.68
     bezeichneter
    0.67
     propOrder
    0.67
     تضيفلها
    0.66
    Activations Density 3.941%

    No Known Activations