© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1724
    Prev
    Next
    INDEX
    Explanations

    the letters "vis" or "Vis"

    oai_token-act-pair · gemini-2.0-flash

    Vis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ChildScrollView
    -0.72
     Egli
    -0.71
     ModelRenderer
    -0.69
    UnknownFields
    -0.64
    Παραπομπές
    -0.62
    geslacht
    -0.61
    SaveChangesAsync
    -0.59
    XmlAccessorType
    -0.58
    INSEE
    -0.58
     stanovnika
    -0.57
    POSITIVE LOGITS
    igo
    0.52
    aler
    0.51
    ca
    0.49
    ic
    0.48
    STS
    0.47
    setId
    0.47
    vertra
    0.45
    alog
    0.45
    lection
    0.44
    na
    0.43
    Activations Density 0.913%

    No Known Activations