© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5959
    Prev
    Next
    INDEX
    Explanations

    positive statements about performance

    oai_token-act-pair · gemini-2.0-flash

    job

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     MainAxisSize
    -1.35
    RenderAtEndOf
    -1.13
     cherchés
    -1.13
    ⓧ
    -1.11
     ujednoznacz
    -1.10
    enumi
    -1.07
    EndProject
    -1.06
    Hochspringen
    -1.05
    Datuak
    -1.05
     يتيمه
    -1.03
    POSITIVE LOGITS
     the
    0.98
    a
    0.77
    ,
    0.76
     and
    0.69
     one
    0.63
     $
    0.60
    o
    0.60
     a
    0.57
     was
    0.57
     three
    0.57
    Activations Density 0.703%

    No Known Activations